LITA: Language Instructed Temporal-Localization Assistant

• URL: http://arxiv.org/abs/2403.19046v1
• Date: Wed, 27 Mar 2024 22:50:48 GMT
• Title: LITA: Language Instructed Temporal-Localization Assistant
• Authors: De-An Huang, Shijia Liao, Subhashree Radhakrishnan, Hongxu Yin, Pavlo Molchanov, Zhiding Yu, Jan Kautz,
• Abstract summary: We introduce time tokens that encode timestamps relative to the video length to better represent time in videos. We also introduce SlowFast tokens in the architecture to capture temporal information at fine temporal resolution. We show that our emphasis on temporal localization also substantially improves video-based text generation compared to existing Video LLMs.
• Score: 71.68815100776278
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: There has been tremendous progress in multimodal Large Language Models (LLMs). Recent works have extended these models to video input with promising instruction following capabilities. However, an important missing piece is temporal localization. These models cannot accurately answer the "When?" questions. We identify three key aspects that limit their temporal localization capabilities: (i) time representation, (ii) architecture, and (iii) data. We address these shortcomings by proposing Language Instructed Temporal-Localization Assistant (LITA) with the following features: (1) We introduce time tokens that encode timestamps relative to the video length to better represent time in videos. (2) We introduce SlowFast tokens in the architecture to capture temporal information at fine temporal resolution. (3) We emphasize temporal localization data for LITA. In addition to leveraging existing video datasets with timestamps, we propose a new task, Reasoning Temporal Localization (RTL), along with the dataset, ActivityNet-RTL, for learning and evaluating this task. Reasoning temporal localization requires both the reasoning and temporal localization of Video LLMs. LITA demonstrates strong performance on this challenging task, nearly doubling the temporal mean intersection-over-union (mIoU) of baselines. In addition, we show that our emphasis on temporal localization also substantially improves video-based text generation compared to existing Video LLMs, including a 36% relative improvement of Temporal Understanding. Code is available at: https://github.com/NVlabs/LITA

Related papers

• TableTime: Reformulating Time Series Classification as Zero-Shot Table Understanding via Large Language Models [54.44272772296578]
  Large language models (LLMs) have demonstrated their effectiveness in multivariate time series classification. LLMs directly encode embeddings for time series within the latent space of LLMs from scratch to align with semantic space of LLMs. We propose TableTime, which reformulates MTSC as a table understanding task.
  arXiv  Detail & Related papers  (2024-11-24T07:02:32Z)
• Temporal Reasoning Transfer from Text to Video [51.68487044397409]
  Video Large Language Models (Video LLMs) struggle with tracking temporal changes and reasoning about temporal relationships. We introduce the Textual Temporal reasoning Transfer (T3) to transfer temporal reasoning abilities from text to video domains. LongVA-7B model achieves competitive performance on comprehensive video benchmarks.
  arXiv  Detail & Related papers  (2024-10-08T16:10:29Z)
• The Surprising Effectiveness of Multimodal Large Language Models for Video Moment Retrieval [36.516226519328015]
  Video-language tasks necessitate spatial and temporal comprehension and require significant compute. This work demonstrates the surprising effectiveness of leveraging image-text pretrained MLLMs for moment retrieval. We achieve a new state-of-the-art in moment retrieval on the widely used benchmarks Charades-STA, QVHighlights, and ActivityNet Captions.
  arXiv  Detail & Related papers  (2024-06-26T06:59:09Z)
• MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval [53.417646562344906]
  Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically matches with a fraction of the prominent video content in the foreground with limited wording diversity. This intrinsic modality imbalance leaves a considerable portion of visual information remaining unaligned with text. In this work, we take an MLLM as a video narrator to generate plausible textual descriptions of the video, thereby mitigating the modality imbalance and boosting the temporal localization.
  arXiv  Detail & Related papers  (2024-06-25T18:39:43Z)
• Language Repository for Long Video Understanding [41.17102343915504]
  This paper introduces a Language Repository (LangRepo) for multi-modal vision LLMs. Our repository maintains concise and structured information as an interpretable (i.e., all-textual) representation.
  arXiv  Detail & Related papers  (2024-03-21T17:59:35Z)
• Self-Chained Image-Language Model for Video Localization and Question Answering [66.86740990630433]
  We propose Self-Chained Video-Answering (SeViLA) framework to tackle both temporal localization and QA on videos. SeViLA framework consists of two modules: Localizer and Answerer, where both are parameter-efficiently fine-tuned from BLIP-2.
  arXiv  Detail & Related papers  (2023-05-11T17:23:00Z)
• Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding [112.3913646778859]
  We propose a simple yet effective video-language modeling framework, S-ViLM. It includes two novel designs, inter-clip spatial grounding and intra-clip temporal grouping, to promote learning region-object alignment and temporal-aware features. S-ViLM surpasses the state-of-the-art methods substantially on four representative downstream tasks.
  arXiv  Detail & Related papers  (2023-03-28T22:45:07Z)

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.