Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding

• URL: http://arxiv.org/abs/2603.05663v1
• Date: Thu, 05 Mar 2026 20:25:32 GMT
• Title: Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding
• Abstract summary: Video Temporal Grounding (VTG) localizes the temporal boundaries of a query-relevant moment in long, untrimmed videos.<n>We propose SemVID, a training-free pruning framework that constructs a compact yet coherent token subset with semantic roles.
• Score: 16.537148896706036
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video Temporal Grounding (VTG) localizes the temporal boundaries of a query-relevant moment in long, untrimmed videos, making video-language-model (VLM) pipelines prohibitively expensive. While recent training-free visual token pruning has shown success in video question answering, naively applying these objectives to VTG often causes drastic degradation, as VTG crucially depends on boundary-sensitive evidence and cross-frame reasoning chains. We therefore identify two VTG-specific pruning principles: Evidence Retention (ER), which keeps query-critical patches especially around event boundaries, and Connectivity Strength (CS), which preserves token-level cross-frame connectivity for long-range evidence aggregation. Building on these insights, we propose SemVID, a training-free pruning framework that constructs a compact yet coherent token subset with complementary semantic roles. SemVID first allocates per-frame token budgets by balancing query relevance and inter-frame variation to avoid over-pruned segments, and then selects three types of tokens: object tokens for diverse query-critical evidence, motion tokens to capture meaningful transitions and serve as cross-frame relays, and a small set of context tokens for scene continuity. Extensive experiments on VTG benchmarks show that SemVID achieves a strong accuracy-efficiency trade-off, retaining up to 95.4% mIoU with only 12.5% visual tokens and delivering up to a 5.8x prefill speedup, consistently outperforming prior methods under the same budgets.

Related papers

• Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding [86.37002814396674]
  We propose Foresee-to-Ground (F2G) for Video Temporal Grounding.<n>F2G integrates Predictive Temporal Perception with Evidence-Driven Reasoning.<n>It consistently improves grounding accuracy across diverse benchmarks.
  arXiv  Detail & Related papers  (2026-05-21T04:03:25Z)
• Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions [75.23170605943457]
  textbfmodel is a framework that decouples reasoning control from memory integration.<n>emphActive Thinking Decision Maker (ATDM) is a transparent reasoning controller that externalizes its decision process.<n>emphHierarchical Progressive Semantic Integration (HPSI) module acts as an efficient memory system.
  arXiv  Detail & Related papers  (2026-04-20T16:15:33Z)
• E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching [87.38371267983263]
  Temporal Video Grounding aims to precisely localize time segments corresponding to query events.<n>E.M.Ground is a novel Vid-LLM for TVG that focuses on holistic and coherent event perception.<n>E.M.Ground consistently outperforms state-of-the-art Vid-LLMs by significant margins.
  arXiv  Detail & Related papers  (2026-02-05T02:16:00Z)
• VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents [33.80068883432077]
  This work presents VTok, a unified video tokenization framework that can be used for both generation and understanding tasks.<n>We propose to decouple the spatial and temporal representations of videos by retaining the spatial features of a single key frame while encoding each subsequent frame into a single residual token.<n>Our experiments suggest that VTok effectively reduces the complexity of video representation from the product of frame count and per-frame token count to their sum.
  arXiv  Detail & Related papers  (2026-02-04T04:39:46Z)
• Dense Video Understanding with Gated Residual Tokenization [49.17263029080152]
  High temporal resolution is essential for capturing fine-grained details in video understanding.<n>Current benchmarks rely mostly on low-frame-rate sampling.<n>Dense Video Understanding (DVU) enables high-FPS video comprehension by reducing both tokenization time and token overhead.
  arXiv  Detail & Related papers  (2025-09-17T17:34:40Z)
• Video-LLMs with Temporal Visual Screening [59.18455762289321]
  Temporal Visual Screening (TVS) is a new task that universally pre-processes video question answering and instruction tuning data.<n>TVS is formulated as a modular front-end adapter task that can be seamlessly integrated into both Video Instruction Tuning (training) and Video Question Answering (inference) pipelines.<n> Experiments demonstrate that incorporating TVS yields relative gains of 7.33% (training) and 34.6% (inference)
  arXiv  Detail & Related papers  (2025-08-27T14:33:32Z)
• When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding [12.410012029024342]
  We present Grounded VideoDiT, a Video LLM designed to overcome limitations by introducing three key innovations.<n>First, a Diffusion Temporal Latent (DTL) encoder enhances boundary sensitivity and maintains temporal consistency.<n>Second, object grounded representations explicitly bind query entities to localized visual evidence, strengthening alignment.<n>Third, a mixed token scheme with discrete temporal timestamp tokens provides explicit modeling, enabling fine grained temporal reasoning.
  arXiv  Detail & Related papers  (2025-08-21T15:12:14Z)
• QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension [86.0749609778104]
  We propose QuoTA, an ante-hoc training-free modular that extends existing large video-language models.<n>QuoTA strategically allocates frame-level importance scores based on query relevance.<n>We decouple the query through Chain-of-Thoughts reasoning to facilitate more precise LVLM-based frame importance scoring.
  arXiv  Detail & Related papers  (2025-03-11T17:59:57Z)
• ViGT: Proposal-free Video Grounding with Learnable Token in Transformer [28.227291816020646]
  Video grounding task aims to locate queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in complex interaction between video and query. We propose a novel boundary regression paradigm that performs regression token learning in a transformer.
  arXiv  Detail & Related papers  (2023-08-11T08:30:08Z)
• Transform-Equivariant Consistency Learning for Temporal Sentence Grounding [66.10949751429781]
  We introduce a novel Equivariant Consistency Regulation Learning framework to learn more discriminative representations for each video. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted. In particular, we devise a self-supervised consistency loss module to enhance the completeness and smoothness of the augmented video.
  arXiv  Detail & Related papers  (2023-05-06T19:29:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.