DEVIAS: Learning Disentangled Video Representations of Action and Scene

• URL: http://arxiv.org/abs/2312.00826v3
• Date: Fri, 6 Sep 2024 07:42:55 GMT
• Title: DEVIAS: Learning Disentangled Video Representations of Action and Scene
• Authors: Kyungho Bae, Geo Ahn, Youngrae Kim, Jinwoo Choi,
• Abstract summary: Video recognition models often learn scene-biased action representation due to the spurious correlation between actions and scenes in the training data. We propose a disentangling encoder-decoder architecture to learn disentangled action and scene representations with a single model. We rigorously validate the proposed method on the UCF-101, Kinetics-400, and HVU datasets for the seen, and the SCUBA, HAT, and HVU datasets for unseen action-scene combination scenarios.
• Score: 3.336126457178601
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video recognition models often learn scene-biased action representation due to the spurious correlation between actions and scenes in the training data. Such models show poor performance when the test data consists of videos with unseen action-scene combinations. Although scene-debiased action recognition models might address the issue, they often overlook valuable scene information in the data. To address this challenge, we propose to learn DisEntangled VIdeo representations of Action and Scene (DEVIAS), for more holistic video understanding. We propose an encoder-decoder architecture to learn disentangled action and scene representations with a single model. The architecture consists of a disentangling encoder (DE), an action mask decoder (AMD), and a prediction head. The key to achieving the disentanglement is employing both DE and AMD during training time. The DE uses the slot attention mechanism to learn disentangled action and scene representations. For further disentanglement, an AMD learns to predict action masks, given an action slot. With the resulting disentangled representations, we can achieve robust performance across diverse scenarios, including both seen and unseen action-scene combinations. We rigorously validate the proposed method on the UCF-101, Kinetics-400, and HVU datasets for the seen, and the SCUBA, HAT, and HVU datasets for unseen action-scene combination scenarios. Furthermore, DEVIAS provides flexibility to adjust the emphasis on action or scene information depending on dataset characteristics for downstream tasks. DEVIAS shows favorable performance in various downstream tasks: Diving48, Something-Something-V2, UCF-101, and ActivityNet. The code is available at https://github.com/KHU-VLL/DEVIAS.

Related papers

• Early Action Recognition with Action Prototypes [62.826125870298306]
  We propose a novel model that learns a prototypical representation of the full action for each class. We decompose the video into short clips, where a visual encoder extracts features from each clip independently. Later, a decoder aggregates together in an online fashion features from all the clips for the final class prediction.
  arXiv  Detail & Related papers  (2023-12-11T18:31:13Z)
• SOAR: Scene-debiasing Open-set Action Recognition [81.8198917049666]
  We propose Scene-debiasing Open-set Action Recognition (SOAR), which features an adversarial scene reconstruction module and an adaptive adversarial scene classification module. The former prevents the decoder from reconstructing the video background given video features, and thus helps reduce the background information in feature learning. The latter aims to confuse scene type classification given video features, with a specific emphasis on the action foreground, and helps to learn scene-invariant information.
  arXiv  Detail & Related papers  (2023-09-03T20:20:48Z)
• Paxion: Patching Action Knowledge in Video-Language Foundation Models [112.92853632161604]
  Action knowledge involves the understanding of textual, visual, and temporal aspects of actions. Recent video-language models' impressive performance on various benchmark tasks reveal their surprising deficiency (near-random performance) in action knowledge. We propose a novel framework, Paxion, along with a new Discriminative Video Dynamics Modeling (DVDM) objective.
  arXiv  Detail & Related papers  (2023-05-18T03:53:59Z)
• Video-Specific Query-Key Attention Modeling for Weakly-Supervised Temporal Action Localization [14.43055117008746]
  Weakly-trimmed temporal action localization aims to identify and localize the action instances in the unsupervised videos with only video-level action labels. We propose a network named VQK-Net with a video-specific query-key attention modeling that learns a unique query for each action category of each input video.
  arXiv  Detail & Related papers  (2023-05-07T04:18:22Z)
• Scene Consistency Representation Learning for Video Scene Segmentation [26.790491577584366]
  We propose an effective Self-Supervised Learning (SSL) framework to learn better shot representations from long-term videos. We present an SSL scheme to achieve scene consistency, while exploring considerable data augmentation and shuffling methods to boost the model generalizability. Our method achieves the state-of-the-art performance on the task of Video Scene.
  arXiv  Detail & Related papers  (2022-05-11T13:31:15Z)
• ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency [62.38914747727636]
  We study self-supervised video representation learning, which is a challenging task due to 1) a lack of labels for explicit supervision and 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video clips as the instances and learn visual representation by discriminating instances from each other. In this paper, we observe that the consistency between positive samples is the key to learn robust video representations.
  arXiv  Detail & Related papers  (2021-06-04T08:44:50Z)
• CoCon: Cooperative-Contrastive Learning [52.342936645996765]
  Self-supervised visual representation learning is key for efficient video analysis. Recent success in learning image representations suggests contrastive learning is a promising framework to tackle this challenge. We introduce a cooperative variant of contrastive learning to utilize complementary information across views.
  arXiv  Detail & Related papers  (2021-04-30T05:46:02Z)
• Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion [86.56202610716504]
  Action categories are highly related with the scene where the action happens, making the model tend to degrade to a solution where only the scene information is encoded. We propose to decouple the scene and the motion (DSM) with two simple operations, so that the model attention towards the motion information is better paid.
  arXiv  Detail & Related papers  (2020-09-12T09:54:11Z)
• Learning Spatiotemporal Features via Video and Text Pair Discrimination [30.64670449131973]
  Cross-modal pair (CPD) framework captures correlation between video and its associated text. We train our CPD models on both standard video dataset (Kinetics-210k) and uncurated web video dataset (-300k) to demonstrate its effectiveness.
  arXiv  Detail & Related papers  (2020-01-16T08:28:57Z)

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.