3rd Place Solution to Meta AI Video Similarity Challenge

• URL: http://arxiv.org/abs/2304.11964v2
• Date: Thu, 18 May 2023 05:37:24 GMT
• Title: 3rd Place Solution to Meta AI Video Similarity Challenge
• Authors: Shuhei Yokoo, Peifei Zhu, Junki Ishikawa, Rintaro Hasegawa
• Abstract summary: This paper presents our 3rd place solution in the Meta AI Video Similarity Challenge (VSC2022) Our approach builds upon existing image copy detection techniques and incorporates several strategies to exploit on the properties of video data.
• Score: 1.1470070927586016
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents our 3rd place solution in both Descriptor Track and Matching Track of the Meta AI Video Similarity Challenge (VSC2022), a competition aimed at detecting video copies. Our approach builds upon existing image copy detection techniques and incorporates several strategies to exploit on the properties of video data, resulting in a simple yet powerful solution. By employing our proposed method, we achieved substantial improvements in accuracy compared to the baseline results (Descriptor Track: 38% improvement, Matching Track: 60% improvement). Our code is publicly available here: https://github.com/line/Meta-AI-Video-Similarity-Challenge-3rd-Place-Solution

Related papers

• Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data [102.0069667710562]
  This paper presents Open-VCLIP++, a framework that adapts CLIP to a strong zero-shot video classifier. We demonstrate that training Open-VCLIP++ is tantamount to continual learning with zero historical data. Our approach is evaluated on three widely used action recognition datasets.
  arXiv  Detail & Related papers  (2023-10-08T04:46:43Z)
• A Similarity Alignment Model for Video Copy Segment Matching [13.517933749704866]
  Meta AI hold Video Similarity Challenge on CVPR 2023 to push the technology forward. We propose a Similarity Alignment Model for video copy segment matching. Our SAM exhibits superior performance compared to other competitors.
  arXiv  Detail & Related papers  (2023-05-25T03:08:51Z)
• A Dual-level Detection Method for Video Copy Detection [13.517933749704866]
  Meta AI hold Video Similarity Challenge on CVPR 2023 to push the technology forward. We propose a dual-level detection method with Video Editing Detection (VED) and Frame Scenes Detection (FSD) to tackle the core challenges on Video Copy Detection.
  arXiv  Detail & Related papers  (2023-05-21T06:19:08Z)
• Feature-compatible Progressive Learning for Video Copy Detection [30.358206867280426]
  Video Copy Detection (VCD) has been developed to identify instances of unauthorized or duplicated video content. This paper presents our second place solutions to the Meta AI Video Similarity Challenge (VSC22), CVPR 2023.
  arXiv  Detail & Related papers  (2023-04-20T13:39:47Z)
• Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022 [28.27029433676475]
  We present the winning solution for ORBIT Few-Shot Video Object Recognition Challenge 2022. Built upon the ProtoNet baseline, the performance of our method is improved with three effective techniques.
  arXiv  Detail & Related papers  (2022-10-01T03:03:20Z)
• Deep Video Prior for Video Consistency and Propagation [58.250209011891904]
  We present a novel and general approach for blind video temporal consistency. Our method is only trained on a pair of original and processed videos directly instead of a large dataset. We show that temporal consistency can be achieved by training a convolutional neural network on a video with Deep Video Prior.
  arXiv  Detail & Related papers  (2022-01-27T16:38:52Z)
• Few-Shot Video Object Detection [70.43402912344327]
  We introduce Few-Shot Video Object Detection (FSVOD) with three important contributions. FSVOD-500 comprises of 500 classes with class-balanced videos in each category for few-shot learning. Our TPN and TMN+ are jointly and end-to-end trained.
  arXiv  Detail & Related papers  (2021-04-30T07:38:04Z)
• NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results [132.53598576262686]
  This paper reviews the first NTIRE challenge on quality enhancement of compressed video. The challenge has three tracks: Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, Track 3 is designed for enhancing the videos compressed by x265 at a fixed bit-rate. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement.
  arXiv  Detail & Related papers  (2021-04-21T22:08:48Z)
• Semi-Supervised Action Recognition with Temporal Contrastive Learning [50.08957096801457]
  We learn a two-pathway temporal contrastive model using unlabeled videos at two different speeds. We considerably outperform video extensions of sophisticated state-of-the-art semi-supervised image recognition methods.
  arXiv  Detail & Related papers  (2021-02-04T17:28:35Z)
• NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results [131.05847851975236]
  This paper reviews the NTIRE 2020 challenge on video quality mapping (VQM) The challenge includes both a supervised track (track 1) and a weakly-supervised track (track 2) for two benchmark datasets. For track 1, in total 7 teams competed in the final test phase, demonstrating novel and effective solutions to the problem. For track 2, some existing methods are evaluated, showing promising solutions to the weakly-supervised video quality mapping problem.
  arXiv  Detail & Related papers  (2020-05-05T15:45:16Z)

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.