PVUW23
* *Pixel-Level Video Understanding in the Wild Challenge
* Motion-state Alignment for Video Semantic Segmentation
* PanopticRoad: Integrated Panoptic Road Segmentation Under Adversarial Conditions
* Perceive, Excavate and Purify: A Novel Object Mining Framework for Instance Segmentation
PVUW24
* *Pixel-Level Video Understanding in the Wild Challenge
* ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models
* SAM-PM: Enhancing Video Camouflaged Object Detection using Spatio-Temporal Attention
PVUW25
* *Pixel-Level Video Understanding in the Wild Challenge
* Adversarially Domain-Adaptive Latent Diffusion for Unsupervised Semantic Segmentation
* Efficient VideoMAE via Temporal Progressive Training
* M-Adaptor: Text-Driven Whole-Body Human Motion Generation
* MTA-VPS: A Large-Scale Benchmark for Video-Based Person Search
* Opentad: a Unified Framework and Comprehensive Study of Temporal Action Detection
* PVUW 2025 Challenge Report: Advances in Pixel-Level Understanding of Complex Videos in the Wild
* REEF: Relevance-Aware and Efficient LLM Adapter for Video Understanding
* Studying Image Diffusion Features for Zero-Shot Video Object Segmentation
9 for PVUW25