CAVE: Competence-Aware Visual Boundary Evidence Alignment for Video Temporal Grounding

• URL: http://arxiv.org/abs/2608.02078v1
• Date: Mon, 03 Aug 2026 11:27:29 GMT
• Title: CAVE: Competence-Aware Visual Boundary Evidence Alignment for Video Temporal Grounding
• Abstract summary: Large vision-language models (LVLMs) have achieved substantial performance gains in Video Temporal Grounding (VTG) through reinforcement learning (RL)<n>Existing methods rely on outcome correctness rewards that evaluate only the final predicted intervals, leaving boundary-related visual evidence insufficiently constrained.<n>We propose Competence-Aware Visual Boundary Alignment (CAVE), which augments localization optimization with boundary-specific visual evidence rewards to timestamp misalignment.
• Score: 37.61837019441122
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large vision-language models (LVLMs) have achieved substantial performance gains in Video Temporal Grounding (VTG) through reinforcement learning (RL). However, existing methods primarily rely on outcome correctness rewards that evaluate only the final predicted intervals, leaving boundary-related visual evidence and its correspondence with timestamp predictions insufficiently constrained. In this paper, we delve into timestamp prediction and its underlying boundary-level visual evidence, showing prevalent misalignment between visual evidence and predicted timestamps across widely used benchmarks. To address this issue, we propose Competence-Aware Visual Boundary Evidence Alignment (CAVE), which augments localization optimization with boundary-specific visual evidence rewards to mitigate evidence-timestamp misalignment. Specifically, to explicitly represent the boundary-specific visual evidence, CAVE introduces boundary-specific evidence tokens and initializes their structured generation and distinct boundary semantics through a lightweight supervised warm-up. During RL, the visual boundary evidence alignment reward reinforces the visual attention of special evidence tokens within the ground-truth boundaries, thereby promoting alignment between visual evidence and temporal boundaries. Moreover, performance-aware gating for evidence supervision is designed to adaptively retain evidence guidance for poorly localized groups while reducing it once localization becomes sufficiently accurate to avoid over-constraining fine-grained boundary refinement. Extensive experiments on several public VTG benchmarks demonstrate the effectiveness of our method.

Related papers

• Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation [50.92223196290564]
  We propose a unified agent loop for explicit evidence selection and consolidation.<n>During exploration, SCoRE retains only query-relevant observations and their source pointers in a maintained textual ledger.<n>At termination, it reloads the referenced original images and consolidates the visual evidence for answering, arranging it into a logical sequence.
  arXiv  Detail & Related papers  (2026-09-14T16:11:35Z)
• VidForensics-M1: Meta-Detection Reinforcement Learning with Verifiable Temporal Grounding for AI-Generated Video Forensics [21.438987128589403]
  We introduce textbfmeta-detection into AI-generated video detection, enabling reliable forgery detection.<n>Based on this insight, we propose an automated data construction pipeline that generates paired real-fake videos.<n>Experiments demonstrate that textbfVidForensics-M1 effectively leverages verifiable temporal evidence to achieve robust and generalizable AI-generated video detection.
  arXiv  Detail & Related papers  (2026-08-11T17:58:10Z)
• TimeThink: Reasoning with Time for Video LLMs [28.549802513886046]
  We propose TimeThink, a reinforcement learning framework that guides temporal evidence discovery in Video-LLMs.<n>Our key idea is to treat temporal clue steps as the fundamental optimization primitive of video reasoning.<n>To enable scalable training, we construct TimeThink-RFT-20K, a dataset with automatically derived temporal evidence segments.
  arXiv  Detail & Related papers  (2026-07-06T13:50:15Z)
• SER: Learning to Ground Video Reasoning with Semantic Evidence Rewards [8.705689021755221]
  We propose Semantic Evidence Reward (SER) to reform RL as a constrained task.<n>Instead of computing pixel-level annotations, SER uses a referee enhancing a VLM to evaluate model-generated evidence claims.<n>On the VLM benchmark, SER achieves 49.6%, improving by 3.0 points over the strong evidence-ground baseline.
  arXiv  Detail & Related papers  (2026-06-23T15:50:33Z)
• SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs [74.89208610190595]
  We present SPOT-E, a test-time method that produces question-conditioned spotlights, optimized per instance via light-weight tuning.<n> SPOT-E yields consistent gains and improved robustness under visual corruptions.
  arXiv  Detail & Related papers  (2026-06-18T13:56:30Z)
• 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)
• Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models [77.3748853516374]
  We propose a training-free, model-intrinsic grounding method for vision-language models.<n>We compute the entropy of the model's next-token distribution and backpropagate it to the visual token embeddings to obtain an entropy-gradient relevance map.<n>We then extract and rank multiple coherent regions to support multi-evidence queries, and introduce an iterative zoom-and-reground procedure with a spatial-entropy stopping rule.
  arXiv  Detail & Related papers  (2026-04-09T16:51:42Z)
• VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification [73.02304272829785]
  VideoBench is a hierarchical benchmark for long-video answering that rigorously verifies evidence.<n>It comprises 500 manually annotated questions across 13 domains, paired with temporal intervals and spatial bounding boxes as evidence.<n>Experiments show that even GeminiPro-3-Pro correctly answers fewer than 17% of questions under the standard end-to-end QA setting.<n>Results expose a significant gap between surface-level answer correctness and genuine evidence-based reasoning.
  arXiv  Detail & Related papers  (2026-04-02T03:29:43Z)
• Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning [55.232400251303794]
  Look As You Think (LAT) is a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution.<n>LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.23% in soft exact match (EM) and 47.0% in IoU@0.5.
  arXiv  Detail & Related papers  (2025-11-15T02:50:23Z)
• Temporal Transductive Inference for Few-Shot Video Object Segmentation [27.140141181513425]
  Few-shot object segmentation (FS-VOS) aims at segmenting video frames using a few labelled examples of classes not seen during initial training. Key to our approach is the use of both global and local temporal constraints. Empirically, our model outperforms state-of-the-art meta-learning approaches in terms of mean intersection over union on YouTube-VIS by 2.8%.
  arXiv  Detail & Related papers  (2022-03-27T14:08:30Z)

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.