SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding

• URL: http://arxiv.org/abs/2504.07745v1
• Date: Thu, 10 Apr 2025 13:40:34 GMT
• Title: SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding
• Authors: Yangliu Hu, Zikai Song, Na Feng, Yawei Luo, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang,
• Abstract summary: Video-based Large Language Models (VideoVid-LLMs) have witnessed substantial advancements in recent years.<n>They struggle with fine-grained understanding, particularly in aspects such as visual dynamics and video details inquiries.<n>To tackle these shortcomings, we find that fine-tuning Video-LLMs on self-supervised fragment tasks greatly improve their fine-grained video understanding abilities.
• Score: 23.96372422130216
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video-based Large Language Models (Video-LLMs) have witnessed substantial advancements in recent years, propelled by the advancement in multi-modal LLMs. Although these models have demonstrated proficiency in providing the overall description of videos, they struggle with fine-grained understanding, particularly in aspects such as visual dynamics and video details inquiries. To tackle these shortcomings, we find that fine-tuning Video-LLMs on self-supervised fragment tasks, greatly improve their fine-grained video understanding abilities. Hence we propose two key contributions:(1) Self-Supervised Fragment Fine-Tuning (SF$^2$T), a novel effortless fine-tuning method, employs the rich inherent characteristics of videos for training, while unlocking more fine-grained understanding ability of Video-LLMs. Moreover, it relieves researchers from labor-intensive annotations and smartly circumvents the limitations of natural language, which often fails to capture the complex spatiotemporal variations in videos; (2) A novel benchmark dataset, namely FineVidBench, for rigorously assessing Video-LLMs' performance at both the scene and fragment levels, offering a comprehensive evaluation of their capabilities. We assessed multiple models and validated the effectiveness of SF$^2$T on them. Experimental results reveal that our approach improves their ability to capture and interpret spatiotemporal details.

Related papers

• SkyReels-V2: Infinite-length Film Generative Model [35.00453687783287]
  We propose SkyReels-V2, an Infinite-length Film Generative Model, that synergizes Multi-modal Large Language Model (MLLM), Multi-stage Pretraining, Reinforcement Learning, and Diffusion Forcing Framework. We establish progressive-resolution pretraining for the fundamental video generation, followed by a four-stage post-training enhancement.
  arXiv  Detail & Related papers  (2025-04-17T16:37:27Z)
• Video Summarization with Large Language Models [41.51242348081083]
  We propose a new video summarization framework that leverages the capabilities of recent Large Language Models (LLMs) Our method, dubbed LLM-based Video Summarization (LLMVS), translates video frames into a sequence of captions using a Muti-modal Large Language Model (MLLM) Our experimental results demonstrate the superiority of the proposed method over existing ones in standard benchmarks.
  arXiv  Detail & Related papers  (2025-04-15T13:56:14Z)
• H2VU-Benchmark: A Comprehensive Benchmark for Hierarchical Holistic Video Understanding [25.111988967973147]
  Existing benchmarks for evaluating video understanding exhibit significant limitations in coverage, task diversity, and scene adaptability.<n>We propose a hierarchical and holistic video understanding benchmark designed to evaluate both general video and online streaming video comprehension.<n>This benchmark contributes three key features: extended video duration, comprehensive assessment tasks, andEnriched video data.
  arXiv  Detail & Related papers  (2025-03-31T12:32:51Z)
• When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning [80.09819072780193]
  We propose a self-supervised framework that leverages Temporal Correspondence for video representation learning (T-CoRe) Experiments of T-CoRe consistently present superior performance across several downstream tasks, demonstrating its effectiveness for video representation learning.
  arXiv  Detail & Related papers  (2025-03-19T10:50:03Z)
• FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding [25.37771142095486]
  We introduce FAVOR-Bench, comprising 1,776 videos with structured manual annotations of various motions.<n>We further build FAVOR-Train, a dataset consisting of 17,152 videos with fine-grained motion annotations.<n>The results of finetuning Qwen2.5-VL on FAVOR-Train yield consistent improvements on motion-related tasks of TVBench, MotionBench and our FAVOR-Bench.
  arXiv  Detail & Related papers  (2025-03-19T06:42:32Z)
• CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval [24.203328970223527]
  We present CaReBench, a testing benchmark for fine-grained video captioning and retrieval.<n>Uniquely, it provides manually separated spatial annotations and temporal annotations for each video.<n>Based on this design, we introduce two evaluation metrics, ReBias and CapST, specifically tailored for video retrieval and video captioning tasks.
  arXiv  Detail & Related papers  (2024-12-31T15:53:50Z)
• STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training [87.58996020705258]
  Video Large Language Models (Video-LLMs) have recently shown strong derivation in basic video understanding tasks. Video-LLMs struggle with compositional reasoning that requires multi-step explicit-temporal inference across object relations, interactions and events. We propose STEP, a novel graph-guided self-training method that enables VideoLLMs to generate reasoning-rich finetuning data from any raw videos to improve itself.
  arXiv  Detail & Related papers  (2024-11-29T11:54:55Z)
• Realizing Video Summarization from the Path of Language-based Semantic Understanding [19.825666473712197]
  We propose a novel video summarization framework inspired by the Mixture of Experts (MoE) paradigm. Our approach integrates multiple VideoLLMs to generate comprehensive and coherent textual summaries.
  arXiv  Detail & Related papers  (2024-10-06T15:03:22Z)
• Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models [53.235170710385006]
  We introduce Grounded-VideoLLM, a novel Video-LLM adept at perceiving and reasoning over specific video moments in a fine-grained manner. We sharpen our model by incorporating (1) an additional temporal stream to encode the relationships between frames and (2) discrete temporal tokens enriched with specific time knowledge. In experiments, Grounded-VideoLLM excels in fine-grained grounding tasks such as temporal sentence grounding, dense video captioning, and grounded VideoQA.
  arXiv  Detail & Related papers  (2024-10-04T10:04:37Z)
• Enhancing Video Transformers for Action Understanding with VLM-aided Training [10.02739652443895]
  We propose a framework that takes advantage of the complementary strengths of ViTs and VLMs. The FTP framework adds processors that focus on specific aspects of human action in videos. We achieve remarkable top-1 accuracy of 93.8% on Kinetics-400 and Something Something-Something V2, surpassing VideoMAEv2 by 2.8% and 2.6%, respectively.
  arXiv  Detail & Related papers  (2024-03-24T12:55:50Z)
• Video Understanding with Large Language Models: A Survey [97.29126722004949]
  Given the remarkable capabilities of large language models (LLMs) in language and multimodal tasks, this survey provides a detailed overview of recent advancements in video understanding. The emergent capabilities Vid-LLMs are surprisingly advanced, particularly their ability for open-ended multi-granularity reasoning. This survey presents a comprehensive study of the tasks, datasets, benchmarks, and evaluation methodologies for Vid-LLMs.
  arXiv  Detail & Related papers  (2023-12-29T01:56:17Z)
• Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos [58.53311308617818]
  We present a new multi-shot video understanding benchmark Shot2Story with detailed shot-level captions, comprehensive video summaries and question-answering pairs. Preliminary experiments show some challenges to generate a long and comprehensive video summary for multi-shot videos. The generated imperfect summaries can already achieve competitive performance on existing video understanding tasks.
  arXiv  Detail & Related papers  (2023-12-16T03:17:30Z)
• MVBench: A Comprehensive Multi-modal Video Understanding Benchmark [63.14000659130736]
  We introduce a comprehensive Multi-modal Video understanding Benchmark, namely MVBench. We first introduce a novel static-to-dynamic method to define these temporal-related tasks. Then, guided by the task definition, we automatically convert public video annotations into multiple-choice QA to evaluate each task.
  arXiv  Detail & Related papers  (2023-11-28T17:59:04Z)
• Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories [56.91664227337115]
  We introduce a collaborative memory mechanism that encodes information across multiple sampled clips of a video at each training iteration. This enables the learning of long-range dependencies beyond a single clip. Our proposed framework is end-to-end trainable and significantly improves the accuracy of video classification at a negligible computational overhead.
  arXiv  Detail & Related papers  (2021-04-02T18:59:09Z)

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.