Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation

• URL: http://arxiv.org/abs/2403.12042v2
• Date: Sat, 6 Jul 2024 04:32:58 GMT
• Title: Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation
• Authors: Zixin Zhu, Xuelu Feng, Dongdong Chen, Junsong Yuan, Chunming Qiao, Gang Hua,
• Abstract summary: We explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We introduce a novel framework, termed "VD-IT", tailored with dedicatedly designed components built upon a fixed T2V model. Our VD-IT achieves highly competitive results, surpassing many existing state-of-the-art methods.
• Score: 72.90144343056227
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding. Our hypothesis is validated through the classic referring video object segmentation (R-VOS) task. We introduce a novel framework, termed "VD-IT", tailored with dedicatedly designed components built upon a fixed pretrained T2V model. Specifically, VD-IT uses textual information as a conditional input, ensuring semantic consistency across time for precise temporal instance matching. It further incorporates image tokens as supplementary textual inputs, enriching the feature set to generate detailed and nuanced masks. Besides, instead of using the standard Gaussian noise, we propose to predict the video-specific noise with an extra noise prediction module, which can help preserve the feature fidelity and elevates segmentation quality. Through extensive experiments, we surprisingly observe that fixed generative T2V diffusion models, unlike commonly used video backbones (e.g., Video Swin Transformer) pretrained with discriminative image/video pre-tasks, exhibit better potential to maintain semantic alignment and temporal consistency. On existing standard benchmarks, our VD-IT achieves highly competitive results, surpassing many existing state-of-the-art methods. The code is available at https://github.com/buxiangzhiren/VD-IT.

Related papers

• Let Video Teaches You More: Video-to-Image Knowledge Distillation using DEtection TRansformer for Medical Video Lesion Detection [91.97935118185]
  We propose Video-to-Image knowledge distillation for the task of medical video lesion detection. By distilling multi-frame contexts into a single frame, the proposed V2I-DETR combines the advantages of utilizing temporal contexts from video-based models and the inference speed of image-based models. V2I-DETR outperforms previous state-of-the-art methods by a large margin while achieving the real-time inference speed (30 FPS) as the image-based model.
  arXiv  Detail & Related papers  (2024-08-26T07:17:05Z)
• CV-VAE: A Compatible Video VAE for Latent Generative Video Models [45.702473834294146]
  Variationalencoders (VAE) plays a crucial role in OpenAI's Auto-temporal compression of videos. Currently, there lacks of a commonly used continuous video (3D) VAE for latent diffusion-based video models. We propose a method for training a video VAE of latent video models, namely CV-VAE, whose latent space is compatible with that of a given image VAE.
  arXiv  Detail & Related papers  (2024-05-30T17:33:10Z)
• DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation [37.25815760042241]
  This paper introduces a new framework, dubbed DirecT2V, to generate text-to-video (T2V) videos. We equip a diffusion model with a novel value mapping method and dual-softmax filtering, which do not require any additional training. The experimental results validate the effectiveness of our framework in producing visually coherent and storyful videos.
  arXiv  Detail & Related papers  (2023-05-23T17:57:09Z)
• Unleashing Text-to-Image Diffusion Models for Visual Perception [84.41514649568094]
  VPD (Visual Perception with a pre-trained diffusion model) is a new framework that exploits the semantic information of a pre-trained text-to-image diffusion model in visual perception tasks. We show that VPD can be faster adapted to downstream visual perception tasks using the proposed VPD.
  arXiv  Detail & Related papers  (2023-03-03T18:59:47Z)
• Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training [70.83385449872495]
  The correlation between the vision and text is essential for video moment retrieval (VMR) Existing methods rely on separate pre-training feature extractors for visual and textual understanding. We propose a generic method, referred to as Visual-Dynamic Injection (VDI), to empower the model's understanding of video moments.
  arXiv  Detail & Related papers  (2023-02-28T19:29:05Z)
• HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training [49.52679453475878]
  We propose a Temporal-Aware video-language pre-training framework, HiTeA, for modeling cross-modal alignment between moments and texts. We achieve state-of-the-art results on 15 well-established video-language understanding and generation tasks.
  arXiv  Detail & Related papers  (2022-12-30T04:27:01Z)
• Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval [70.30052749168013]
  Multi-channel video-language retrieval require models to understand information from different channels. contrastive multimodal models are shown to be highly effective at aligning entities in images/videos and text. There is not a clear way to quickly adapt these two lines to multi-channel video-language retrieval with limited data and resources.
  arXiv  Detail & Related papers  (2022-06-05T01:43:52Z)

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.