A video-LLM that uses diffusion features, segmentation-guided object tokens, and discrete time tokens to improve temporal grounding, but its claimed SOTA results are not supported by its own tables.
Videotree: Adaptive tree-based video representation for llm reasoning on long videos,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding
A video-LLM that uses diffusion features, segmentation-guided object tokens, and discrete time tokens to improve temporal grounding, but its claimed SOTA results are not supported by its own tables.