ECCV 2026 | 长视频Token剪枝新范式：从关键帧到证据链
Ranking
Overall
74
Content
85
Popularity
47
Observed public metrics from 1 member.
Merged summary
TL;DR - SemVID is a training-free visual-token pruning method for long-video temporal grounding that preserves an “evidence chain” rather than isolated keyframes. It reduces inference cost while maintaining accurate event-boundary localization under aggressive token compression.
- SemVID allocates per-frame token budgets using both query relevance and inter-frame changes, retaining evidence across the event timeline.
- It preserves complementary object, motion, and context tokens to capture relevant entities, temporal transitions, and scene continuity.
- Motion tokens serve as cross-frame relay nodes, while MMR selection prevents redundant object patches from consuming the token budget.
- On Charades-STA and ActivityNet-Grounding with Qwen3-VL and Qwen2.5-VL, SemVID outperformed existing pruning methods in localization and evidence-retention/connectivity metrics at equal budgets, particularly at low retention rates.
Sources (1)
ECCV 2026 | 长视频Token剪枝新范式：从关键帧到证据链
Public signals
Semantic Scholar citations 4 · Semantic Scholar influential citations 0
TL;DR - SemVID is a training-free visual-token pruning method for long-video temporal grounding that preserves an “evidence chain” rather than isolated keyframes. It reduces inference cost while maintaining accurate event-boundary localization under aggressive token compression.
- SemVID allocates per-frame token budgets using both query relevance and inter-frame changes, retaining evidence across the event timeline.
- It preserves complementary object, motion, and context tokens to capture relevant entities, temporal transitions, and scene continuity.
- Motion tokens serve as cross-frame relay nodes, while MMR selection prevents redundant object patches from consuming the token budget.
- On Charades-STA and ActivityNet-Grounding with Qwen3-VL and Qwen2.5-VL, SemVID outperformed existing pruning methods in localization and evidence-retention/connectivity metrics at equal budgets, particularly at low retention rates.