@article{bb247400,
AUTHOR = "Zhang, Y. and Bian, S. and Liu, J. and Song, R.J. and Zhu, D. and Zhang, C.H. and Hua, C.C.",
TITLE = "Robot Active Task Cognition:
Situation-Aware Task Planning With Large Language Models",
JOURNAL = CirSysVideo,
VOLUME = "36",
YEAR = "2026",
NUMBER = "4",
MONTH = "April",
PAGES = "4722-4733",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242292"}
@article{bb247401,
AUTHOR = "Yin, J.H. and Pu, N. and Zhang, X.Y. and Yang, L.F. and Wu, L. and Wang, X.J. and Zhong, Z.",
TITLE = "Plug-and-play Class-aware Knowledge Injection for Prompt Learning with
Visual-Language Model",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "6",
MONTH = "June",
PAGES = "254",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242293"}
@article{bb247402,
AUTHOR = "Yang, J.H. and Jiang, M. and Zhao, Q.",
TITLE = "Defying Distractions in Multimodal Tasks: A Novel Benchmark for Large
Vision-Language Models",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "6",
MONTH = "June",
PAGES = "6314-6331",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242294"}
@article{bb247403,
AUTHOR = "Wang, X.W.",
TITLE = "TriFusion-RL: Integrating task verifiers, self-feedback, and
perceptual tools for vision-language models",
JOURNAL = CVIU,
VOLUME = "268",
YEAR = "2026",
PAGES = "104764",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242295"}
@article{bb247404,
AUTHOR = "Chen, W.X. and Su, H.",
TITLE = "Enhancing Multimodal Compositional Understanding of Vision-Language
Models With Semantic Decoupling and Feature Coupling",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3102-3106",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242296"}
@article{bb247405,
AUTHOR = "Sun, Y.W. and Liu, C.B. and Fang, S.C. and Li, P.D. and Lu, Z.Y. and Xie, H.T.",
TITLE = "RoFLIP: Robust and Fine-Grained Alignment for Vision-Language
Compositional Reasoning",
JOURNAL = IJCV,
VOLUME = "134",
YEAR = "2026",
NUMBER = "9",
MONTH = "September",
PAGES = "401",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242297"}
@article{bb247406,
AUTHOR = "Xiang, K. and Zhang, T.J.C. and Huang, Y. and He, J.X. and Liu, Z. and Tang, Y.L. and Zhou, R.Z. and Luo, L. and Wen, Y.P. and Chen, X. and Lin, B.Q. and Han, J.H. and Xu, H. and Li, H. and Dong, B. and Liang, X.D.",
TITLE = "Aligning Perception, Reasoning, Modeling and Interaction:
A Survey on Physical AI",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "10",
MONTH = "October",
PAGES = "12938-12957",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242298"}
@article{bb247407,
AUTHOR = "Yan, J. and Dong, B. and Guan, X.Y. and Zheng, W.S. and Zhang, T. and Wang, R.X.",
TITLE = "Adaptively Fine-Tuning and Ensembling Vision-Language Model for
Few-Shot Image Classification",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "6770-6783",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242299"}
@article{bb247408,
AUTHOR = "Sun, X.Y. and Zou, X.G. and Wu, Y.Q. and Zhang, S.T. and Wang, G.",
TITLE = "Fair fine-tuning of medical vision-language models via learned
textual embedding of sensitive attributes",
JOURNAL = PR,
VOLUME = "182",
YEAR = "2027",
PAGES = "114701",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242300"}
@article{bb247409,
AUTHOR = "Yuan, P. and Ma, A. and Yao, Y.C. and Yao, H.X. and Tomizuka, M. and Ding, M.Y.",
TITLE = "REMAC: Self-reflective and self-evolving multi-agent collaboration
for long-horizon robot manipulation",
JOURNAL = PR,
VOLUME = "182",
YEAR = "2027",
PAGES = "114831",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242301"}
@article{bb247410,
AUTHOR = "Zhang, C. and Liu, F. and Xu, Y. and An, Y.X. and Cao, S.H. and Deng, C.",
TITLE = "Making Large Vision-Language Models Better Few-Shot Learners",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "10286-10299",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242302"}
@article{bb247411,
AUTHOR = "Li, B. and Zhang, Z.C. and Liu, S. and Yu, W.H. and Wang, X.C.",
TITLE = "Top-Down Compression: Revisit Efficient Vision Token Projection for
Visual Instruction Tuning",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "10332-10346",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242303"}
@inproceedings{bb247412,
AUTHOR = "Kim, M.",
TITLE = "PerVL-Bench: Benchmarking Multimodal Personalization for Large
Vision-Language Models",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "6696-6704",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242304"}
@inproceedings{bb247413,
AUTHOR = "Kawarada, M. and Yamada, K. and Tejero de Pablos, A. and Inoue, N.",
TITLE = "Training-free Conditional Image Embedding Framework Leveraging Large
Vision Language Models",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "7636-7646",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242305"}
@inproceedings{bb247414,
AUTHOR = "Fahim, M. and Rahman, M.S.U. and Rahman, A.M. and Ishmam, M.F. and Rahman, M.T. and Shifat, F.T. and Haider, F. and Bhuiyan, M.F.A.",
TITLE = "BanglaProtha: Evaluating Vision Language Models in Underrepresented
Long-tail Cultural Contexts",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "1159-1169",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242306"}
@inproceedings{bb247415,
AUTHOR = "Lin, Z.X. and Haghighat, M. and Browne, W. and Miller, D.",
TITLE = "Intra-Class Probabilistic Embeddings for Uncertainty Estimation in
Vision-Language Models",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "2327-2337",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242307"}
@inproceedings{bb247416,
AUTHOR = "Gu, D.F. and Gao, Y.H. and Zhou, M. and Metaxas, D.N.",
TITLE = "Anatomy-VLM: A Fine-grained Vision-Language Model for Medical
Interpretation",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "2838-2847",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242308"}
@inproceedings{bb247417,
AUTHOR = "Zamini, M. and Shukla, D.",
TITLE = "Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient
Vision-Language Models",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "3648-3657",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242309"}
@inproceedings{bb247418,
AUTHOR = "Saravanan, D. and Tapaswi, M. and Gandhi, V.",
TITLE = "Investigating Mechanisms for In-Context Vision Language Binding",
BOOKTITLE = InterpVis25,
YEAR = "2025",
PAGES = "4852-4856",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242310"}
@inproceedings{bb247419,
AUTHOR = "Selvam, S. and Rajendran, R.K. and Sankaradas, M. and Raghunathan, A. and Chakradhar, S.T.",
TITLE = "SimCache: Similarity Caching for Efficient VLM-based Scene
Understanding",
BOOKTITLE = LargeVM25,
YEAR = "2025",
PAGES = "3318-3327",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242311"}
@inproceedings{bb247420,
AUTHOR = "Tushar, P. and Pandey, E. and Austria, L.D.B. and Loo, Y.Y. and Lim, J.H. and Atmosukarto, I. and Lock, D.S.C.",
TITLE = "MerCulture: A Comprehensive Benchmark to Evaluate Vision-Language
Models on Cultural Understanding in Singapore",
BOOKTITLE = "AIBench25",
YEAR = "2025",
PAGES = "565-574",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242312"}
@inproceedings{bb247421,
AUTHOR = "Ma, Z.Y. and Gou, C. and Shi, H. and Sun, B. and Li, S.T. and Rezatofighi, H. and Cai, J.F.",
TITLE = "DrVideo: Document Retrieval Based Long Video Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18936-18946",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242313"}
@inproceedings{bb247422,
AUTHOR = "Dhouib, M. and Buscaldi, D. and Vanier, S. and Shabou, A.",
TITLE = "PACT: Pruning and Clustering-Based Token Reduction for Faster Visual
Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14582-14592",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242314"}
@inproceedings{bb247423,
AUTHOR = "Nath, V. and Li, W.Q. and Yang, D. and Myronenko, A. and Zheng, M.X. and Lu, Y. and Liu, Z.J. and Yin, H.X. and Law, Y.M. and Tang, Y.C. and Guo, P.F. and Zhao, C. and Xu, Z.Y. and He, Y.F. and Harmon, S. and Simon, B. and Heinrich, G. and Aylward, S. and Edgar, M. and Zephyr, M. and Molchanov, P. and Turkbey, B. and Roth, H. and Xu, D.",
TITLE = "VILA-M3: Enhancing Vision-Language Models with Medical Expert
Knowledge",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14788-14798",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242315"}
@inproceedings{bb247424,
AUTHOR = "Du, H. and Wu, B. and Lu, Y. and Mao, Z.D.",
TITLE = "SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic
Video Situation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13798-13809",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242316"}
@inproceedings{bb247425,
AUTHOR = "Kaduri, O. and Bagon, S. and Dekel, T.",
TITLE = "What's in the Image? A Deep-Dive into the Vision of Vision Language
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14549-14558",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242317"}
@inproceedings{bb247426,
AUTHOR = "Xing, L. and Huang, Q.D. and Dong, X.Y. and Lu, J.J. and Zhang, P. and Zang, Y.H. and Cao, Y.H. and He, C.H. and Wang, J.Q. and Wu, F. and Lin, D.",
TITLE = "Conical Visual Concentration for Efficient Large Vision-Language
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14593-14603",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242318"}
@inproceedings{bb247427,
AUTHOR = "Zhang, L. and Yang, Q. and Agrawal, A.",
TITLE = "Assessing and Learning Alignment of Unimodal Vision and Language
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14604-14614",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242319"}
@inproceedings{bb247428,
AUTHOR = "Sehgal, A. and Yuan, P. and Hu, Z. and Yue, Y.S. and Sun, J.J. and Chaudhuri, S.",
TITLE = "Self-Evolving Visual Concept Library using Vision-Language Critics",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13124-13134",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242320"}
@inproceedings{bb247429,
AUTHOR = "Wang, W.H. and Wang, L. and Gu, X.T. and Huang, S.Y. and Dong, Y.X. and Tang, J.",
TITLE = "MotionBench: Benchmarking and Improving Fine-Grained Video Motion
Understanding for Vision Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8450-8460",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242321"}
@inproceedings{bb247430,
AUTHOR = "Nacson, M.S. and Aberdam, A. and Ganz, R. and Avraham, E.B. and Golts, A. and Kittenplon, Y. and Mazor, S. and Litman, R.",
TITLE = "DocVLM: Make Your VLM an Efficient Reader",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29005-29015",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242322"}
@inproceedings{bb247431,
AUTHOR = "Alhamoud, K. and Alshammari, S. and Tian, Y.L. and Li, G.H. and Torr, P.H.S. and Kim, Y. and Ghassemi, M.",
TITLE = "Vision-Language Models Do Not Understand Negation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29612-29622",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242323"}
@inproceedings{bb247432,
AUTHOR = "Schmalfuss, J. and Chang, N. and VS, V. and Shen, M. and Bruhn, A. and Alvarez, J.M.",
TITLE = "PARC: A Quantitative Framework Uncovering the Symmetries within
Vision Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "25081-25091",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242324"}
@inproceedings{bb247433,
AUTHOR = "Xiao, J.Q. and Sang, S. and Zhi, T.C. and Liu, J. and Yan, Q. and Luo, L.J. and Yuan, B.",
TITLE = "COAP: Memory-Efficient Training with Correlation-Aware Gradient
Projection",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "30116-30126",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242325"}
@inproceedings{bb247434,
AUTHOR = "Zhu, Y.Q. and Wang, Z.Y. and Zhang, C. and Li, P. and Liu, Y.",
TITLE = "CoSpace: Benchmarking Continuous Space Perception Ability for
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29569-29579",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242326"}
@inproceedings{bb247435,
AUTHOR = "Kang, H.Q. and Sachdeva, E. and Gupta, P. and Bae, S.J. and Lee, K.",
TITLE = "GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models
with Generative Flow Networks",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3815-3825",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242327"}
@inproceedings{bb247436,
AUTHOR = "Zhang, K. and Li, J.Y. and Li, Z. and Zhou, S.K.",
TITLE = "DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid
Set-Embeddings Learning",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24993-25003",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242328"}
@inproceedings{bb247437,
AUTHOR = "Saravanan, D. and Gupta, V. and Singh, D. and Khan, Z. and Gandhi, V. and Tapaswi, M.",
TITLE = "VELOCITI: Benchmarking Video-Language Compositional Reasoning with
Strict Entailment",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18914-18924",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242329"}
@inproceedings{bb247438,
AUTHOR = "Pan, B. and Li, Q. and Tang, X.Y. and Huang, W. and Fang, Z. and Liu, F. and Wang, J.Y. and Yu, J.Y. and Shi, Y.",
TITLE = "NLPrompt: Noise-Label Prompt Learning for Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19963-19973",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242330"}
@inproceedings{bb247439,
AUTHOR = "Zhang, Y.T. and Chen, L. and Zheng, G.D. and Gao, Y.F. and Zheng, R. and Fu, J. and Yin, Z.F. and Jin, S. and Qiao, Y. and Huang, X.J. and Zhao, F. and Gui, T. and Shao, J.",
TITLE = "SPA-VL: A Comprehensive Safety Preference Alignment Dataset for
Vision Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19867-19878",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242331"}
@inproceedings{bb247440,
AUTHOR = "Zhou, E. and Su, Q. and Chi, C. and Zhang, Z.Z. and Wang, Z.Y. and Huang, T.J. and Sheng, L. and Wang, H.",
TITLE = "Code-as-Monitor: Constraint-aware Visual Programming for Reactive and
Proactive Robotic Failure Detection",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "6919-6929",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242332"}
@inproceedings{bb247441,
AUTHOR = "Song, C.H. and Blukis, V. and Tremblay, J. and Tyree, S. and Su, Y. and Birchfield, S.",
TITLE = "RoboSpatial: Teaching Spatial Understanding to 2D and 3D
Vision-Language Models for Robotics",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "15768-15780",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242333"}
@inproceedings{bb247442,
AUTHOR = "Lozano, A. and Sun, M.W. and Burgess, J. and Chen, L. and Nirschl, J.J. and Gu, J. and Lopez, I. and Aklilu, J. and Rau, A. and Katzer, A.W. and Zhang, Y.H. and Chiu, C. and Wang, X.H. and Song, A.S. and Tibshirani, R. and Yeung Levy, S.",
TITLE = "BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and
Vision-Language Models Derived from Scientific Literature",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19724-19735",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242334"}
@inproceedings{bb247443,
AUTHOR = "Xiao, R. and Kim, S. and Georgescu, M.I. and Akata, Z. and Alaniz, S.",
TITLE = "FLAIR: VLM with Fine-grained Language-informed Image Representations",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24884-24894",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242335"}
@inproceedings{bb247444,
AUTHOR = "Vasu, P.K.A. and Faghri, F. and Li, C.L. and Koc, C. and True, N. and Antony, A. and Santhanam, G. and Gabriel, J. and Grasch, P. and Tuzel, O. and Pouransari, H.",
TITLE = "FastVLM: Efficient Vision Encoding for Vision Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19769-19780",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242336"}
@inproceedings{bb247445,
AUTHOR = "Chen, Q.Z. and Wang, C. and Wang, D. and Zhang, T. and Li, W. and He, X.F.",
TITLE = "Lifelong Knowledge Editing for Vision Language Models with Low-Rank
Mixture-of-Experts",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "9455-9466",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242337"}
@inproceedings{bb247446,
AUTHOR = "Liu, Z.J. and Zhu, L. and Shi, B. and Zhang, Z.Y. and Lou, Y.M. and Yang, S. and Xi, H.C. and Cao, S.Y. and Gu, Y.X. and Li, D.C. and Li, X. and Tang, H.T. and Fang, Y.H. and Chen, Y. and Hsieh, C.Y. and Huang, D.A. and Cheng, A.C. and Hu, J.Y. and Liu, S. and Krishna, R. and Molchanov, P. and Kautz, J. and Yin, H.X. and Han, S. and Lu, Y.",
TITLE = "NVILA: Efficient Frontier Visual Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4122-4134",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242338"}
@inproceedings{bb247447,
AUTHOR = "Zhang, H.Y. and Guo, Y.Y. and Kankanhalli, M.",
TITLE = "Joint Vision-Language Social Bias Removal for CLIP",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4246-4255",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242339"}
@inproceedings{bb247448,
AUTHOR = "Deng, A. and Cao, T. and Chen, Z. and Hooi, B.",
TITLE = "Words or Vision: Do Vision-Language Models Have Blind Faith in Text?",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3867-3876",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242340"}
@inproceedings{bb247449,
AUTHOR = "Huang, R. and Ding, X.P. and Wang, C.W. and Han, J.H. and Liu, Y.L. and Zhao, H.S. and Xu, H. and Hou, L. and Zhang, W. and Liang, X.D.",
TITLE = "HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29814-29824",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242341"}
@inproceedings{bb247450,
AUTHOR = "Wang, S. and Zhang, Y.J. and Zhu, Y. and Li, J.N. and Wang, Z.Z. and Liu, Y.W. and Ji, X.Y.",
TITLE = "Towards Understanding How Knowledge Evolves in Large Vision-Language
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29858-29868",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242342"}
@inproceedings{bb247451,
AUTHOR = "Zhao, W. and Han, Y.Z. and Tang, J.S. and Li, Z. and Song, Y.B. and Wang, K. and Wang, Z.Y. and You, Y.",
TITLE = "A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for
Accelerating Large VLMs",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19814-19824",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242343"}
@inproceedings{bb247452,
AUTHOR = "Safaei, B. and Patel, V.M.",
TITLE = "Active Learning for Vision-Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4902-4912",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242344"}
@inproceedings{bb247453,
AUTHOR = "Wang, Y.C. and Zhang, Z.K. and Wang, J. and Fan, D. and Xu, Z.L. and Liu, L. and Hao, X. and Bhat, V. and Li, X.Y.",
TITLE = "GEXIA: Granularity Expansion and Iterative Approximation for Scalable
Multi-Grained Video-Language Learning",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4725-4735",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242345"}
@inproceedings{bb247454,
AUTHOR = "Colman, R. and Vu, M. and Bhattarai, M. and Ma, M. and Viswanathan, H. and O'Malley, D. and Santos, J.E.",
TITLE = "PatchFinder: Leveraging Visual Language Models for Accurate
Information Retrieval Using Model Uncertainty",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9146-9155",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242346"}
@inproceedings{bb247455,
AUTHOR = "Jawade, B. and Soares, J.V.B. and Thadani, K. and Mohan, D.D. and Eshratifar, A.E. and Culpepper, B. and de Juan, P. and Setlur, S. and Govindaraju, V.",
TITLE = "SCOT: Self-Supervised Contrastive Pretraining for Zero-Shot
Compositional Retrieval",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5509-5519",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242347"}
@inproceedings{bb247456,
AUTHOR = "Chang, H.S. and Wang, C.Y. and Wang, R.R. and Chou, G. and Liao, H.Y.M.",
TITLE = "Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual
Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6217-6227",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242348"}
@inproceedings{bb247457,
AUTHOR = "Chen, H.N. and Ni, Y. and Huang, W.J. and Liu, Y. and Jeong, S. and Wen, F. and Bastian, N.D. and Latapie, H. and Imani, M.",
TITLE = "VLTP: Vision-Language Guided Token Pruning for Task-Oriented
Segmentation",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9353-9363",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242349"}
@inproceedings{bb247458,
AUTHOR = "Yamada, M. and Dharamshi, N. and Kohli, A. and Kasu, P. and Khan, A. and Ghulyani, M.",
TITLE = "Unleashing Potentials of Vision-Language Models for Zero-Shot HOI
Detection",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5751-5760",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242350"}
@inproceedings{bb247459,
AUTHOR = "Ghoddoosian, R. and Agarwal, N. and Dwivedi, I. and Darisuh, B.",
TITLE = "ACE: Action Concept Enhancement of Video-Language Models in
Procedural Videos",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9521-9531",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242351"}
@inproceedings{bb247460,
AUTHOR = "Onoe, Y. and Rane, S. and Berger, Z. and Bitton, Y. and Cho, J. and Garg, R. and Ku, A. and Parekh, Z. and Pont Tuset, J. and Tanzer, G. and Wang, S. and Baldridge, J.",
TITLE = "DOCCI: Descriptions of Connected and Contrasting Images",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LX: 291-309",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242352"}
@inproceedings{bb247461,
AUTHOR = "Li, T. and Ma, M.M. and Peng, X.",
TITLE = "DEAL: Disentangle and Localize Concept-level Explanations for VLMs",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXIX: 383-401",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242353"}
@inproceedings{bb247462,
AUTHOR = "Li, S.C. and Li, L. and Liu, Y. and Ren, S.H. and Liu, Y.X. and Gao, R.D. and Sun, X. and Hou, L.",
TITLE = "Vitatecs: A Diagnostic Dataset for Temporal Concept Understanding of
Video-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXX: 331-348",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242354"}
@inproceedings{bb247463,
AUTHOR = "Rahmanzadehgervi, P. and Bolton, L. and Taesiri, M.R. and Nguyen, A.T.",
TITLE = "Vision Language Models are blind",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "V: 293-309",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242355"}
@inproceedings{bb247464,
AUTHOR = "Chytas, S.P. and Kim, H.W.J. and Singh, V.",
TITLE = "Understanding Multi-compositional Learning in Vision and Language
Models via Category Theory",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLVIII: 324-341",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242356"}
@inproceedings{bb247465,
AUTHOR = "Song, Y.Z. and Chen, Y.S. and Lin, T.L. and Liu, B. and Fu, J.L. and Shuai, H.H.",
TITLE = "Capture Concept Through Comparison: Vision-and-language Representation
Learning with Intrinsic Information Mining",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 220-238",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242357"}
@inproceedings{bb247466,
AUTHOR = "He, H.C. and Liu, W.B. and Xing, W.W.",
TITLE = "Biefficient: Bidirectionally Prompting Vision-language Models for
Parameter-efficient Video Recognition",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 257-274",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242358"}
@inproceedings{bb247467,
AUTHOR = "Yang, J.K. and Dong, Y.H. and Liu, S. and Li, B. and Wang, Z.Y. and Tan, H.R. and Jiang, C.C. and Kang, J. and Zhang, Y.H. and Zhou, K.Y. and Liu, Z.W.",
TITLE = "Octopus: Embodied Vision-language Programmer from Environmental
Feedback",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "I: 20-38",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242359"}
@inproceedings{bb247468,
AUTHOR = "Kar, O.F. and Tonioni, A. and Poklukar, P. and Kulshrestha, A. and Zamir, A. and Tombari, F.",
TITLE = "Brave: Broadening the Visual Encoding of Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVI: 113-132",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242360"}
@inproceedings{bb247469,
AUTHOR = "Kamath, A. and Hsieh, C.Y. and Chang, K.W. and Krishna, R.",
TITLE = "The Hard Positive Truth About Vision-language Compositionality",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIV: 37-54",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242361"}
@inproceedings{bb247470,
AUTHOR = "Jia, B.X. and Chen, Y.X. and Yu, H.Y. and Wang, Y. and Niu, X.S. and Liu, T.Y. and Li, Q. and Huang, S.Y.",
TITLE = "Sceneverse: Scaling 3d Vision-language Learning for Grounded Scene
Understanding",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "IX: 289-310",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242362"}
@inproceedings{bb247471,
AUTHOR = "Zhang, Y.F. and Jiang, M. and Zhao, Q.",
TITLE = "Learning Chain of Counterfactual Thought for Bias-robust
Vision-language Reasoning",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "VIII: 334-351",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242363"}
@inproceedings{bb247472,
AUTHOR = "Li, J. and Chen, D. and Cai, T. and Chen, P.H. and Hong, Y. and Chen, Z.F. and Shen, Y.K. and Gan, C.",
TITLE = "Flexattention for Efficient High-resolution Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXV: 286-302",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242364"}
@inproceedings{bb247473,
AUTHOR = "Li, X. and Ding, J. and Chen, Z.Y. and Elhoseiny, M.",
TITLE = "UNI3DL: A Unified Model for 3d Vision-language Understanding",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXIII: 74-92",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242365"}
@inproceedings{bb247474,
AUTHOR = "Hao, T.X. and Ding, X.H. and Feng, J.X. and Yang, Y.H. and Chen, H. and Ding, G.",
TITLE = "Quantized Prompt for Efficient Generalization of Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIX: 54-73",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242366"}
@inproceedings{bb247475,
AUTHOR = "Xu, H.B. and Ke, X. and Li, Y.Z. and Xu, R. and Wu, H.Q. and Lin, X.F. and Guo, W.Z.",
TITLE = "Vision-language Action Knowledge Learning for Semantic-aware Action
Quality Assessment",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLII: 423-440",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242367"}
@inproceedings{bb247476,
AUTHOR = "Zhu, Z.Y. and Zhang, Z. and Ma, X.J. and Niu, X.S. and Chen, Y.X. and Jia, B.X. and Deng, Z.D. and Huang, S.Y. and Li, Q.",
TITLE = "Unifying 3d Vision-language Understanding via Promptable Queries",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIV: 188-206",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242368"}
@inproceedings{bb247477,
AUTHOR = "Jiang, H.B. and Yue, J.P. and Luo, H. and Ding, Z. and Lu, Z.Q.",
TITLE = "Reinforcement Learning Friendly Vision-language Model for Minecraft",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXVIII: 1-17",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242369"}
@inproceedings{bb247478,
AUTHOR = "Nguyen, A.T. and Tai, K.S. and Chen, B.C. and Shukla, S.N. and Yu, H.C. and Torr, P.H.S. and Tian, T.P. and Lim, S.N.",
TITLE = "ucap: An Unsupervised Prompting Method for Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXIV: 425-439",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242370"}
@inproceedings{bb247479,
AUTHOR = "Zhang, Y. and Yu, K. and Wu, S.Q. and He, Z.H.",
TITLE = "Conceptual Codebook Learning for Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXVII: 235-251",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242371"}
@inproceedings{bb247480,
AUTHOR = "Chatterjee, A. and Luo, Y.R. and Gokhale, T. and Yang, Y.Z. and Baral, C.",
TITLE = "Revision: Rendering Tools Enable Spatial Fidelity in Vision-language
Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXX: 339-357",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242372"}
@inproceedings{bb247481,
AUTHOR = "Sharma, P. and Shaham, T.R. and Baradad, M. and Rodriiuez Munoz, A. and Duggal, S. and Isola, P. and Torralba, A. and Fu, S.",
TITLE = "A Vision Check-up for Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14410-14419",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242373"}
@inproceedings{bb247482,
AUTHOR = "Parodi, F. and Matelsky, J.K. and Regla Vargas, A. and Foglia, E.E. and Lim, C. and Weinberg, D. and Kording, K.P. and Herrick, H.M. and Platt, M.L.",
TITLE = "Vision-language models for decoding provider attention during
neonatal resuscitation",
BOOKTITLE = CVPM24,
YEAR = "2024",
PAGES = "343-353",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242374"}
@inproceedings{bb247483,
AUTHOR = "Li, L. and Guan, H.Y. and Qiu, J.N. and Spratling, M.",
TITLE = "One Prompt Word is Enough to Boost Adversarial Robustness for
Pre-Trained Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "24408-24419",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242375"}
@inproceedings{bb247484,
AUTHOR = "Cui, J.Q. and Zhu, B. and Wen, X. and Qi, X.J. and Yu, B. and Zhang, H.W.",
TITLE = "Classes Are Not Equal: An Empirical Study on Image Recognition
Fairness",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23283-23292",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242376"}
@inproceedings{bb247485,
AUTHOR = "Stojnic, V. and Kalantidis, Y. and Tolias, G.",
TITLE = "Label Propagation for Zero-shot Classification with Vision-Language
Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23209-23218",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242377"}
@inproceedings{bb247486,
AUTHOR = "Yuan, T.T. and Zhang, X. and Liu, K. and Liu, B. and Chen, C. and Jin, J. and Jiao, Z.Z.",
TITLE = "Towards Surveillance Video-and-Language Understanding: New Dataset,
Baselines, and Challenges",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "22052-22061",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242378"}
@inproceedings{bb247487,
AUTHOR = "Mittal, H. and Agarwal, N. and Lo, S.Y. and Lee, K.",
TITLE = "Can't make an Omelette without Breaking some Eggs: Plausible Action
Anticipation using Large Video-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18580-18590",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242379"}
@inproceedings{bb247488,
AUTHOR = "Zhao, G.L. and Li, G.B. and Chen, W.K. and Yu, Y.Z.",
TITLE = "OVER-NAV: Elevating Iterative Vision-and-Language Navigation with
Open-Vocabulary Detection and StructurEd Representation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16296-16306",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242380"}
@inproceedings{bb247489,
AUTHOR = "Li, X. and Wu, Y.F. and Jiang, X.H. and Guo, Z.H. and Gong, M.M. and Cao, H.Y. and Liu, Y.S. and Jiang, D.Q. and Sun, X.",
TITLE = "Enhancing Visual Document Understanding with Contrastive Learning in
Large Visual-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "15546-15555",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242381"}
@inproceedings{bb247490,
AUTHOR = "Pham, K. and Huynh, C. and Lim, S.N. and Shrivastava, A.",
TITLE = "Composing Object Relations and Attributes for Image-Text Matching",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14354-14363",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242382"}
@inproceedings{bb247491,
AUTHOR = "Xu, Z.L. and Zhu, Y. and Deng, S.Q. and Mittal, A. and Chen, Y.B. and Wang, M. and Favaro, P. and Tighe, J. and Modolo, D.",
TITLE = "Benchmarking Zero-Shot Recognition with Vision-Language Models:
Challenges on Granularity and Specificity",
BOOKTITLE = WhatNext24,
YEAR = "2024",
PAGES = "1827-1836",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242383"}
@inproceedings{bb247492,
AUTHOR = "Luo, Z.W. and Gustafsson, F.K. and Zhao, Z. and Sjolund, J. and Schon, T.B.",
TITLE = "Photo-Realistic Image Restoration in the Wild with Controlled
Vision-Language Models",
BOOKTITLE = NTIRE24,
YEAR = "2024",
PAGES = "6641-6651",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242384"}
@inproceedings{bb247493,
AUTHOR = "Pan, C. and Yaman, B. and Nesti, T. and Mallik, A. and Allievi, A.G. and Velipasalar, S. and Ren, L.",
TITLE = "VLP: Vision Language Planning for Autonomous Driving",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14760-14769",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242385"}
@inproceedings{bb247494,
AUTHOR = "Liang, M. and Su, J.C. and Schulter, S. and Garg, S. and Zhao, S.Y. and Wu, Y. and Chandraker, M.",
TITLE = "AIDE: An Automatic Data Engine for Object Detection in Autonomous
Driving",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14695-14706",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242386"}
@inproceedings{bb247495,
AUTHOR = "Li, Z. and Li, X. and Fu, X. and Zhang, X. and Wang, W.Q. and Chen, S. and Yang, J.",
TITLE = "PromptKD: Unsupervised Prompt Distillation for Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26607-26616",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242387"}
@inproceedings{bb247496,
AUTHOR = "Zhang, L. and Awal, R. and Agrawal, A.",
TITLE = "Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to
Enhance Visio-Linguistic Compositional Understanding",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13774-13784",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242388"}
@inproceedings{bb247497,
AUTHOR = "Rosasco, A. and Berti, S. and Pasquale, G. and Malafronte, D. and Sato, S. and Segawa, H. and Inada, T. and Natale, L.",
TITLE = "ConCon-Chi: Concept-Context Chimera Benchmark for Personalized
Vision-Language Tasks",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "22239-22248",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242389"}
@inproceedings{bb247498,
AUTHOR = "Cheng, S. and Guo, Z.C. and Wu, J. and Fang, K. and Li, P. and Liu, H.P. and Liu, Y.",
TITLE = "EgoThink: Evaluating First-Person Perspective Thinking Capability of
Vision-Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14291-14302",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242390"}
@inproceedings{bb247499,
AUTHOR = "Kil, J. and Song, C.H. and Zheng, B. and Deng, X. and Su, Y. and Chao, W.L.",
TITLE = "Dual-View Visual Contextualization for Web Navigation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14445-14454",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT242391"}
Last update:Oct 8, 2026 at 11:03:09