VideoLLM-online: Online Video Large Language Model for Streaming Video

• URL: http://arxiv.org/abs/2406.11816v1
• Date: Mon, 17 Jun 2024 17:55:32 GMT
• Title: VideoLLM-online: Online Video Large Language Model for Streaming Video
• Authors: Joya Chen, Zhaoyang Lv, Shiwei Wu, Kevin Qinghong Lin, Chenan Song, Difei Gao, Jia-Wei Liu, Ziteng Gao, Dongxing Mao, Mike Zheng Shou,
• Abstract summary: We propose a novel Learning-In-Video-Stream framework, which enables temporally aligned, long-context, and real-time conversation within a continuous video stream. Our framework supports streaming dialogue in a 5-minute video clip at over 10 FPS on an A100 GPU. It also showcases state-of-the-art performance on public offline video benchmarks, such as recognition, captioning, and forecasting.
• Score: 27.073238234038826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent Large Language Models have been enhanced with vision capabilities, enabling them to comprehend images, videos, and interleaved vision-language content. However, the learning methods of these large multimodal models typically treat videos as predetermined clips, making them less effective and efficient at handling streaming video inputs. In this paper, we propose a novel Learning-In-Video-Stream (LIVE) framework, which enables temporally aligned, long-context, and real-time conversation within a continuous video stream. Our LIVE framework comprises comprehensive approaches to achieve video streaming dialogue, encompassing: (1) a training objective designed to perform language modeling for continuous streaming inputs, (2) a data generation scheme that converts offline temporal annotations into a streaming dialogue format, and (3) an optimized inference pipeline to speed up the model responses in real-world video streams. With our LIVE framework, we built VideoLLM-online model upon Llama-2/Llama-3 and demonstrate its significant advantages in processing streaming videos. For instance, on average, our model can support streaming dialogue in a 5-minute video clip at over 10 FPS on an A100 GPU. Moreover, it also showcases state-of-the-art performance on public offline video benchmarks, such as recognition, captioning, and forecasting. The code, model, data, and demo have been made available at https://showlab.github.io/videollm-online.

Related papers

• Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams [78.72965584414368]
  We present Flash-VStream, a video-language model that simulates the memory mechanism of human. Compared to existing models, Flash-VStream achieves significant reductions in latency inference and VRAM consumption. We propose VStream-QA, a novel question answering benchmark specifically designed for online video streaming understanding.
  arXiv  Detail & Related papers  (2024-06-12T11:07:55Z)
• InternVideo2: Scaling Foundation Models for Multimodal Video Understanding [51.129913789991924]
  InternVideo2 is a new family of video foundation models (FM) that achieve state-of-the-art results in video recognition, video-speech tasks, and video-centric tasks. Our core design is a progressive training approach that unifies the masked video modeling, cross contrastive learning, and prediction token, scaling up to 6B video size.
  arXiv  Detail & Related papers  (2024-03-22T17:57:42Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• VideoPoet: A Large Language Model for Zero-Shot Video Generation [78.57171527944774]
  VideoPoet is a language model capable of synthesizing high-quality video with matching audio. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs.
  arXiv  Detail & Related papers  (2023-12-21T18:46:41Z)
• Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream [5.215681853828831]
  We propose an efficient video learning approach to learn from a long, untrimmed streaming video. To the best of our knowledge, we are the first attempt to directly learn from the on-device, long video stream.
  arXiv  Detail & Related papers  (2022-08-25T13:41:03Z)
• Revealing Single Frame Bias for Video-and-Language Learning [115.01000652123882]
  We show that a single-frame trained model can achieve better performance than existing methods that use multiple frames for training. This result reveals the existence of a strong "static appearance bias" in popular video-and-language datasets. We propose two new retrieval tasks based on existing fine-grained action recognition datasets that encourage temporal modeling.
  arXiv  Detail & Related papers  (2022-06-07T16:28:30Z)
• End-to-end Generative Pretraining for Multimodal Video Captioning [82.79187814057313]
  We present Multimodal Video Generative Pretraining (MV-GPT), a new pretraining framework for learning from unlabelled videos. Unlike recent video-language pretraining frameworks, our framework trains both a multimodal video encoder and a sentence decoder jointly. Our model achieves state-of-the-art performance for multimodal video captioning on four standard benchmarks.
  arXiv  Detail & Related papers  (2022-01-20T16:16:21Z)

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.