Text-Guided Video Masked Autoencoder

• URL: http://arxiv.org/abs/2408.00759v1
• Date: Thu, 1 Aug 2024 17:58:19 GMT
• Title: Text-Guided Video Masked Autoencoder
• Authors: David Fan, Jue Wang, Shuai Liao, Zhikang Zhang, Vimal Bhat, Xinyu Li,
• Abstract summary: We introduce a novel text-guided masking algorithm (TGM) that masks the video regions with highest correspondence to paired captions. We show that across existing masking algorithms, unifying MAE and masked video-text contrastive learning improves downstream performance compared to pure MAE.
• Score: 12.321239366215426
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such visual cues depends on how often input videos match underlying assumptions. On the other hand, natural language description is an information dense representation of video that implicitly captures saliency without requiring modality-specific assumptions, and has not been explored yet for video MAE. To this end, we introduce a novel text-guided masking algorithm (TGM) that masks the video regions with highest correspondence to paired captions. Without leveraging any explicit visual cues for saliency, our TGM is competitive with state-of-the-art masking algorithms such as motion-guided masking. To further benefit from the semantics of natural language for masked reconstruction, we next introduce a unified framework for joint MAE and masked video-text contrastive learning. We show that across existing masking algorithms, unifying MAE and masked video-text contrastive learning improves downstream performance compared to pure MAE on a variety of video recognition tasks, especially for linear probe. Within this unified framework, our TGM achieves the best relative performance on five action recognition and one egocentric datasets, highlighting the complementary nature of natural language for masked video modeling.

Related papers

• SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing [19.245228801339007]
  We propose a novel framework called SegTalker to decouple lip movements and image textures. We disentangle semantic regions of image into style codes using a mask-guided encoder. Ultimately, we inject the previously generated talking segmentation and style codes into a mask-guided StyleGAN to synthesize video frame.
  arXiv  Detail & Related papers  (2024-09-05T15:11:40Z)
• ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders [53.3185750528969]
  Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework. We introduce a data-independent method, termed ColorMAE, which generates different binary mask patterns by filtering random noise. We demonstrate our strategy's superiority in downstream tasks compared to random masking.
  arXiv  Detail & Related papers  (2024-07-17T22:04:00Z)
• Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition [56.968108142307976]
  We propose a novel approach called Class-Aware Mask-guided feature refinement (CAM) Our approach introduces canonical class-aware glyph masks to suppress background and text style noise. By enhancing the alignment between the canonical mask feature and the text feature, the module ensures more effective fusion.
  arXiv  Detail & Related papers  (2024-02-21T09:22:45Z)
• Siamese Masked Autoencoders [76.35448665609998]
  We present Siamese Masked Autoencoders (SiamMAE) for learning visual correspondence from videos. SiamMAE operates on pairs of randomly sampled video frames and asymmetrically masks them. It outperforms state-of-the-art self-supervised methods on video object segmentation, pose keypoint propagation, and semantic part propagation tasks.
  arXiv  Detail & Related papers  (2023-05-23T17:59:46Z)
• Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval [19.61947785487129]
  Mask for Semantics Completion (MASCOT) based on semantic-based masked modeling. Our MASCOT performs state-of-the-art performance on four major text-video retrieval benchmarks.
  arXiv  Detail & Related papers  (2023-05-13T12:31:37Z)
• Improving Masked Autoencoders by Learning Where to Mask [65.89510231743692]
  Masked image modeling is a promising self-supervised learning method for visual data. We present AutoMAE, a framework that uses Gumbel-Softmax to interlink an adversarially-trained mask generator and a mask-guided image modeling process. In our experiments, AutoMAE is shown to provide effective pretraining models on standard self-supervised benchmarks and downstream tasks.
  arXiv  Detail & Related papers  (2023-03-12T05:28:55Z)
• Masked Contrastive Pre-Training for Efficient Video-Text Retrieval [37.05164804180039]
  We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pretraining (MAC) Our MAC aims to reduce video representation's spatial and temporal redundancy in the VidLP model. Coupling these designs enables efficient end-to-end pre-training: reduce FLOPs (60% off), accelerate pre-training (by 3x), and improve performance.
  arXiv  Detail & Related papers  (2022-12-02T05:44:23Z)
• MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining [138.86293836634323]
  MaskCLIP incorporates a newly proposed masked self-distillation into contrastive language-image pretraining. MaskCLIP achieves superior results in linear probing, finetuning, and zero-shot performance with the guidance of the language encoder.
  arXiv  Detail & Related papers  (2022-08-25T17:59:58Z)
• MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining [68.05105411320842]
  We propose a novel approach MaskOCR to unify vision and language pre-training in the classical encoder-decoder recognition framework. We adopt the masked image modeling approach to pre-train the feature encoder using a large set of unlabeled real text images. We transform text data into synthesized text images to unify the data modalities of vision and language, and enhance the language modeling capability of the sequence decoder.
  arXiv  Detail & Related papers  (2022-06-01T08:27:19Z)
• MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval [43.2299969152561]
  Methods for text-to-video retrieval on four datasets with both zero-shot and fine-tune evaluation protocols. Our method outperforms state-of-the-art methods for text-to-video retrieval on four datasets with both zero-shot and fine-tune evaluation protocols.
  arXiv  Detail & Related papers  (2022-04-26T16:06:31Z)

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.