Related papers: Spatiotemporal Inconsistency Learning for DeepFake…
With the rapid development of digital multimedia, video understanding has become an important field. For action recognition, temporal dimension plays an important role, and this is quite different from image recognition. In order to learn…
Recently, tactile sensing has attracted great interest in robotics, especially for facilitating exploration of unstructured environments and effective manipulation. A detailed understanding of the surface textures via tactile sensing is…
Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel…
Large-scale video-language pretraining enables strong generalization across multimodal tasks but often incurs prohibitive computational costs. Although recent advances in masked visual modeling help mitigate this issue, they still suffer…
Video large language models have achieved remarkable performance in tasks such as video question answering, however, their temporal understanding remains suboptimal. To address this limitation, we curate a dedicated instruction fine-tuning…
The drastic variation of motion in spatial and temporal dimensions makes the video prediction task extremely challenging. Existing RNN models obtain higher performance by deepening or widening the model. They obtain the multi-scale features…
Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…
Existing audio-driven visual dubbing methods have achieved great success. Despite this, we observe that the semantic ambiguity between spatial and temporal domains significantly degrades the synthesis stability for the dynamic faces. We…
A major challenge in DeepFake forgery detection is that state-of-the-art algorithms are mostly trained to detect a specific fake method. As a result, these approaches show poor generalization across different types of facial manipulations,…
In this report, our approach to tackling the task of ActivityNet 2018 Kinetics-600 challenge is described in detail. Though spatial-temporal modelling methods, which adopt either such end-to-end framework as I3D \cite{i3d} or two-stage…
Face anti-spoofing is critical to the security of face recognition systems. Depth supervised learning has been proven as one of the most effective methods for face anti-spoofing. Despite the great success, most previous works still…
Image pre-training, the current de-facto paradigm for a wide range of visual tasks, is generally less favored in the field of video recognition. By contrast, a common strategy is to directly train with spatiotemporal convolutional neural…
Applying Multimodal Large Language Models (MLLMs) to video understanding presents significant challenges due to the need to model temporal relations across frames. Existing approaches adopt either implicit temporal modeling, relying solely…
Video inpainting aims to fill spatio-temporal "corrupted" regions with plausible content. To achieve this goal, it is necessary to find correspondences from neighbouring frames to faithfully hallucinate the unknown content. Current methods…
Multi-level features are important for saliency detection. Better combination and use of multi-level features with time information can greatly improve the accuracy of the video saliency model. In order to fully combine multi-level features…
In this paper, we present a spatio-temporal tendency reasoning (STR) network for recovering human body pose and shape from videos. Previous approaches have focused on how to extend 3D human datasets and temporal-based learning to promote…
Point cloud videos capture dynamic 3D motion while reducing the effects of lighting and viewpoint variations, making them highly effective for recognizing subtle and continuous human actions. Although Selective State Space Models (SSMs)…
Video Large Language Models (VideoLLMs) have shown remarkable progress in video understanding. However, these models still struggle to effectively perceive and exploit rich temporal information in videos when responding to user queries.…
Deep spatiotemporal models are used in a variety of computer vision tasks, such as action recognition and video object segmentation. Currently, there is a limited understanding of what information is captured by these models in their…
Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current predictive models, which lead to image distortion and…