Pith. sign in

REVIEW 9 cited by

TRACE: Temporal Grounding Video LLM via Causal Event Modeling

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.05643 v3 pith:3NY6UC6Y submitted 2024-10-08 cs.CV

Yongxin Guo , Jingyu Liu , Mingda Li , Qingbin Liu , Xi Chen , Xiaoying Tang This is my paper · ORCID
classification cs.CV
keywords videoeventtaskstracecausalmodelingframeworkvarious
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively handle various tasks simultaneously and enable zero-shot prediction, there is a growing trend in employing video LLMs for VTG tasks. However, current video LLM-based methods rely exclusively on natural language generation, lacking the ability to model the clear structure inherent in videos, which restricts their effectiveness in tackling VTG tasks. To address this issue, this paper first formally introduces causal event modeling framework, which represents video LLM outputs as sequences of events, and predict the current event using previous events, video inputs, and textural instructions. Each event consists of three components: timestamps, salient scores, and textual captions. We then propose a novel task-interleaved video LLM called TRACE to effectively implement the causal event modeling framework in practice. The TRACE process visual frames, timestamps, salient scores, and text as distinct tasks, employing various encoders and decoding heads for each. Task tokens are arranged in an interleaved sequence according to the causal event modeling framework's formulation. Extensive experiments on various VTG tasks and datasets demonstrate the superior performance of TRACE compared to state-of-the-art video LLMs. Our model and code are available at https://github.com/gyxxyg/TRACE.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding

    cs.CV 2025-08 conditional novelty 7.0 of 10

    A reinforcement-learning method that forces video grounding models to emit progressively more accurate intermediate timestamps, improving accuracy and reasoning faithfulness without large teacher models.

  2. Your VLM Already Knows When: Training-Free Temporal Grounding by Asking Yes or No

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A zero-training method that turns temporal grounding into a coarse-to-fine scan of binary clip questions beats direct timestamp prediction by 28 to 50 R@0.5 points on four frozen VLMs.

  3. Number it: Temporal Grounding Videos like Flipping Manga

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Number-Prompt overlays frame numbers on video frames, improving temporal grounding in video LLMs and setting new state-of-the-art results on moment retrieval and highlight detection.

  4. TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech

    cs.AI 2026-01 reject novelty 5.0 of 10

    TANDEM reports 0.73 target-F1 on HateMM for structured video hate detection, but its novelty claims rest on a missing RL-without-SCCR baseline and misleading SOTA comparisons.

  5. Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Temporal Grounding

    cs.CV 2025-08 conditional novelty 5.0 of 10

    Rollout-averaged pseudo labels with variance-based confidence weighting let a GRPO-trained temporal grounding model adapt to an unlabelled target domain from only 100-200 videos.

  6. Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

    cs.CV 2025-06 reject novelty 5.0 of 10

    PAM extends SAM 2 with a frozen LLM and a Semantic Perceiver to jointly segment and describe regions in images, videos, and streaming video, and contributes a 0.6M-sample region-level streaming video caption dataset.

  7. Video-Text Temporal Localization via Multi-Scale Convolution and Dynamic Routing

    cs.CV 2026-07 conditional novelty 4.5 of 10

    Multi-scale temporal convolutions plus capsule routing improve video-text moment localization to 42.9% R@0.5 and 41.1% mIoU on ActivityNet Captions.

  8. Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey

    cs.CL 2024-12 conditional novelty 4.0 of 10

    A survey maps the field of MLLM explainability and interpretability into data, model, and training and inference perspectives.

  9. Do Language Models Understand Time?

    cs.CV 2024-12 conditional novelty 3.0 of 10

    A survey arguing that video-LLMs rely on pretrained encoders and short-biased datasets, leaving them weak at long-term temporal reasoning such as causality and event progression.

Pith tools