TimeRefine: Temporal Grounding with Time Refining Video LLM

• URL: http://arxiv.org/abs/2412.09601v1
• Date: Thu, 12 Dec 2024 18:59:11 GMT
• Title: TimeRefine: Temporal Grounding with Time Refining Video LLM
• Authors: Xizi Wang, Feng Cheng, Ziyang Wang, Huiyu Wang, Md Mohaiminul Islam, Lorenzo Torresani, Mohit Bansal, Gedas Bertasius, David Crandall,
• Abstract summary: Video temporal grounding aims to localize relevant temporal boundaries in a video given a textual prompt. We reformulate the temporal grounding task as a temporal refining task. We incorporate an auxiliary prediction head that penalizes the model more if a predicted segment deviates further from the ground truth.
• Score: 75.99665302872901
• License:
• Abstract: Video temporal grounding aims to localize relevant temporal boundaries in a video given a textual prompt. Recent work has focused on enabling Video LLMs to perform video temporal grounding via next-token prediction of temporal timestamps. However, accurately localizing timestamps in videos remains challenging for Video LLMs when relying solely on temporal token prediction. Our proposed TimeRefine addresses this challenge in two ways. First, instead of directly predicting the start and end timestamps, we reformulate the temporal grounding task as a temporal refining task: the model first makes rough predictions and then refines them by predicting offsets to the target segment. This refining process is repeated multiple times, through which the model progressively self-improves its temporal localization accuracy. Second, to enhance the model's temporal perception capabilities, we incorporate an auxiliary prediction head that penalizes the model more if a predicted segment deviates further from the ground truth, thus encouraging the model to make closer and more accurate predictions. Our plug-and-play method can be integrated into most LLM-based temporal grounding approaches. The experimental results demonstrate that TimeRefine achieves 3.6% and 5.0% mIoU improvements on the ActivityNet and Charades-STA datasets, respectively. Code and pretrained models will be released.

Related papers

• Temporal Preference Optimization for Long-Form Video Understanding [28.623353303256653]
  Temporal Preference Optimization (TPO) is a novel post-training framework designed to enhance the temporal grounding capabilities of video-LMMs. TPO significantly enhances temporal understanding while reducing reliance on manually annotated data. LLaVA-Video-TPO establishes itself as the leading 7B model on the Video-MME benchmark.
  arXiv  Detail & Related papers  (2025-01-23T18:58:03Z)
• Predicting Long-horizon Futures by Conditioning on Geometry and Time [49.86180975196375]
  We explore the task of generating future sensor observations conditioned on the past. We leverage the large-scale pretraining of image diffusion models which can handle multi-modality. We create a benchmark for video prediction on a diverse set of videos spanning indoor and outdoor scenes.
  arXiv  Detail & Related papers  (2024-04-17T16:56:31Z)
• Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning [22.28251586213348]
  aLLM4TS is an innovative framework that adapts Large Language Models (LLMs) for time-series representation learning. A distinctive element of our framework is the patch-wise decoding layer, which departs from previous methods reliant on sequence-level decoding.
  arXiv  Detail & Related papers  (2024-02-07T13:51:26Z)
• AutoTimes: Autoregressive Time Series Forecasters via Large Language Models [67.83502953961505]
  AutoTimes projects time series into the embedding space of language tokens and autoregressively generates future predictions with arbitrary lengths. We formulate time series as prompts, extending the context for prediction beyond the lookback window. AutoTimes achieves state-of-the-art with 0.1% trainable parameters and over $5times$ training/inference speedup.
  arXiv  Detail & Related papers  (2024-02-04T06:59:21Z)
• MomentDiff: Generative Video Moment Retrieval from Random to Real [71.40038773943638]
  We provide a generative diffusion-based framework called MomentDiff. MomentDiff simulates a typical human retrieval process from random browsing to gradual localization. We show that MomentDiff consistently outperforms state-of-the-art methods on three public benchmarks.
  arXiv  Detail & Related papers  (2023-07-06T09:12:13Z)
• 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)
• Split Time Series into Patches: Rethinking Long-term Series Forecasting with Dateformer [17.454822366228335]
  Time is one of the most significant characteristics of time-series, yet has received insufficient attention. We propose Dateformer who turns attention to modeling time instead of following the above practice. Dateformer yields state-of-the-art accuracy with a 40% remarkable relative improvement, and broadens the maximum credible forecasting range to a half-yearly level.
  arXiv  Detail & Related papers  (2022-07-12T08:58:44Z)
• EVOQUER: Enhancing Temporal Grounding with Video-Pivoted BackQuery Generation [10.799980374791316]
  Temporal grounding aims to predict a time interval of a video clip corresponding to a natural language query input. We present EVOQUER, a temporal grounding framework incorporating an existing text-to-video grounding model and a video-assisted query generation network.
  arXiv  Detail & Related papers  (2021-09-10T00:30:36Z)
• Deconfounded Video Moment Retrieval with Causal Intervention [80.90604360072831]
  We tackle the task of video moment retrieval (VMR), which aims to localize a specific moment in a video according to a textual query. Existing methods primarily model the matching relationship between query and moment by complex cross-modal interactions. We propose a causality-inspired VMR framework that builds structural causal model to capture the true effect of query and video content on the prediction.
  arXiv  Detail & Related papers  (2021-06-03T01:33:26Z)

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.