COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark

• URL: http://arxiv.org/abs/2408.02272v1
• Date: Mon, 5 Aug 2024 07:00:10 GMT
• Title: COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark
• Authors: Koki Maeda, Tosho Hirasawa, Atsushi Hashimoto, Jun Harashima, Leszek Rybicki, Yusuke Fukasawa, Yoshitaka Ushiku,
• Abstract summary: We propose a new dataset, COM Kitchens, which consists of unedited overhead-view videos captured by smartphones. We propose the novel video-to-text retrieval task Online Recipe Retrieval (OnRR) and new video captioning domain Dense Video Captioning on unedited Overhead-View videos (DVC-OV) Our experiments verified the capabilities and limitations of current web-video-based SOTA methods in handling these tasks.
• Score: 13.623338371949337
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Procedural video understanding is gaining attention in the vision and language community. Deep learning-based video analysis requires extensive data. Consequently, existing works often use web videos as training resources, making it challenging to query instructional contents from raw video observations. To address this issue, we propose a new dataset, COM Kitchens. The dataset consists of unedited overhead-view videos captured by smartphones, in which participants performed food preparation based on given recipes. Fixed-viewpoint video datasets often lack environmental diversity due to high camera setup costs. We used modern wide-angle smartphone lenses to cover cooking counters from sink to cooktop in an overhead view, capturing activity without in-person assistance. With this setup, we collected a diverse dataset by distributing smartphones to participants. With this dataset, we propose the novel video-to-text retrieval task Online Recipe Retrieval (OnRR) and new video captioning domain Dense Video Captioning on unedited Overhead-View videos (DVC-OV). Our experiments verified the capabilities and limitations of current web-video-based SOTA methods in handling these tasks.

Related papers

• DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering [13.466266412068475]
  We introduce the DocVideoQA task and dataset for the first time, comprising 1454 videos across 23 categories with a total duration of about 828 hours. The dataset is annotated with 154k question-answer pairs generated manually and via GPT, assessing models' comprehension, temporal awareness, and modality integration capabilities. Our method enhances unimodal feature extraction with diverse instruction-tuning data and employs contrastive learning to strengthen modality integration.
  arXiv  Detail & Related papers  (2025-03-20T06:21:25Z)
• ViLCo-Bench: VIdeo Language COntinual learning Benchmark [8.660555226687098]
  We present ViLCo-Bench, designed to evaluate continual learning models across a range of video-text tasks. The dataset comprises ten-minute-long videos and corresponding language queries collected from publicly available datasets. We introduce a novel memory-efficient framework that incorporates self-supervised learning and mimics long-term and short-term memory effects.
  arXiv  Detail & Related papers  (2024-06-19T00:38:19Z)
• CinePile: A Long Video Question Answering Dataset and Benchmark [55.30860239555001]
  We present a novel dataset and benchmark, CinePile, specifically designed for authentic long-form video understanding. Our comprehensive dataset comprises 305,000 multiple-choice questions (MCQs), covering various visual and multimodal aspects. We fine-tuned open-source Video-LLMs on the training split and evaluated both open-source and proprietary video-centric LLMs on the test split of our dataset.
  arXiv  Detail & Related papers  (2024-05-14T17:59:02Z)
• Composed Video Retrieval via Enriched Context and Discriminative Embeddings [118.66322242183249]
  Composed video retrieval (CoVR) is a challenging problem in computer vision. We introduce a novel CoVR framework that leverages detailed language descriptions to explicitly encode query-specific contextual information. Our approach achieves gains as high as around 7% in terms of recall@K=1 score.
  arXiv  Detail & Related papers  (2024-03-25T17:59:03Z)
• Detours for Navigating Instructional Videos [58.1645668396789]
  We propose VidDetours, a video-language approach that learns to retrieve the targeted temporal segments from a large repository of how-to's. We show our model's significant improvements over best available methods for video retrieval and question answering, with recall rates exceeding the state of the art by 35%.
  arXiv  Detail & Related papers  (2024-01-03T16:38:56Z)
• InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation [90.71796406228265]
  InternVid is a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations. The InternVid dataset contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accompanied by detailed descriptions of total 4.1B words.
  arXiv  Detail & Related papers  (2023-07-13T17:58:32Z)
• A Survey on Deep Learning Technique for Video Segmentation [147.0767454918527]
  Video segmentation plays a critical role in a broad range of practical applications. Deep learning based approaches have been dedicated to video segmentation and delivered compelling performance.
  arXiv  Detail & Related papers  (2021-07-02T15:51:07Z)
• Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [80.7397409377659]
  We propose an end-to-end trainable model that is designed to take advantage of both large-scale image and video captioning datasets. Our model is flexible and can be trained on both image and video text datasets, either independently or in conjunction. We show that this approach yields state-of-the-art results on standard downstream video-retrieval benchmarks.
  arXiv  Detail & Related papers  (2021-04-01T17:48:27Z)
• A Comprehensive Review on Recent Methods and Challenges of Video Description [11.69687792533269]
  Video description involves the generation of the natural language description of actions, events, and objects in the video. There are various applications of video description by filling the gap between languages and vision for visually impaired people. In the past decade, several works had been done in this field in terms of approaches/methods for video description, evaluation metrics, and datasets.
  arXiv  Detail & Related papers  (2020-11-30T13:08:45Z)
• VLEngagement: A Dataset of Scientific Video Lectures for Evaluating Population-based Engagement [23.078055803229912]
  Video lectures have become one of the primary modalities to impart knowledge to masses in the current digital age. There is still an important need for data and research aimed at understanding learner engagement with scientific video lectures. This paper introduces VLEngagement, a novel dataset that consists of content-based and video-specific features extracted from publicly available scientific video lectures.
  arXiv  Detail & Related papers  (2020-11-02T14:20:19Z)

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.