MoVISA: Multi-Token Reasoning for Video Object Segmentation
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
MoVISA introduces Multi-Token Reasoning for Video Object Segmentation, using multiple segmentation tokens (e.g., SEG0, SEG1) instead of a single token to better localize multiple objects over time. This approach enhances fine-grained alignment between language prompts and spatio-temporal mask predictions, leading to improved performance and interpretability. On benchmarks such as MeViS, DAVIS17, ReVOS, and Ref-Youtube-VOS, MoVISA achieves significant gains, notably a 13.2% J and F improvement on MeViS and an 8.4% J and F improvement on ReVOS.
TrajTok introduces an end‑to‑end video tokenizer that replaces traditional patchification with a lightweight, trajectory‑based tokenization process. It performs implicit clustering over space‑time pixels to generate object trajectories in a single forward pass, dynamically adjusting token granularity to semantic complexity while remaining independent of video duration. The resulting TrajViT2 model outperforms existing methods on classification and retrieval benchmarks, and TrajTok can also serve as a probing head (TrajAdapter) or alignment connector (TrajVLM) for vision‑language tasks, notably improving long‑video reasoning.
arXiv:2501.04001v4 Announce Type: replace Abstract: This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-...
Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates context windows and incurs prohibitive costs. Curre...
arXiv:2609.37042v1 Announce Type: cross Abstract: Video Large Language Models (VideoLLMs) have achieved strong video understanding capabilities but incur substantial inference overhead due to the lar...
arXiv:2505.01583v2 Announce Type: replace Abstract: Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models (VLM...