arXiv Computer Vision
MLLM-Assisted Audio VOS: A 3rd Place Report for the MeViS-Audio Track, 8th LSVOS Challenge
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Sep 24
MoVISA: Multi-Token Reasoning for Video Object Segmentation
Recent advances in video object segmentation with Multimodal Large Language Model (MLLM) reasoning have demonstrated the effectiveness of using a single textual token, such as SEG, to predict segmenta...
arXiv Computer Vision
Aug 27
ARGenSeg: Image Segmentation with Autoregressive Image Generation Model
ARGenSeg introduces an autoregressive generation-based approach for image segmentation that integrates seamlessly with multimodal large language models (MLLMs). Unlike prior methods that use boundary points or dedicated segmentation heads, ARGenSeg generates dense masks directly through visual token output and detokenization via a universal VQ‑VAE, enabling fine‑grained pixel‑level perception. The framework employs a next‑scale‑prediction strategy to parallelize token generation, resulting in faster inference while outperforming state‑of‑the‑art segmentation models on multiple datasets.
arXiv AI
Jun 3
AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes
arXiv:2606. 02724v1 Announce Type: cross Abstract: Audio-visual speaker tracking aims to localize and track active speakers by leveraging auditory and visual cues, enabling fine-grained, human-centric scene understanding.
arXiv Computer Vision
Aug 25
Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos
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-...
arXiv Computer Vision
Sep 25
MoVISA: Multi-Token Reasoning for Video Object Segmentation
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.
Hugging Face Trending Papers
Sep 15
Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos?
Multimodal Large Language Models have demonstrated impressive video understanding, yet their ability to reason over long-form narratives is often masked by visual-centric evaluations and inefficient c...