Related papers: CPGA: Coding Priors-Guided Aggregation Network for…
Video action recognition has made significant strides, but challenges remain in effectively using both spatial and temporal information. While existing methods often focus on either spatial features (e.g., object appearance) or temporal…
Recently, Users Generated Content (UGC) videos becomes ubiquitous in our daily lives. However, due to the limitations of photographic equipments and techniques, UGC videos often contain various degradations, in which one of the most…
Temporal Graph Neural Networks (TGNNs) are powerful models to capture temporal, structural, and contextual information on temporal graphs. The generated temporal node embeddings outperform other methods in many downstream tasks. Real-world…
The ever-increasing demand for 3D modeling in the emerging immersive applications has made point clouds an essential class of data for 3D image and video processing. Tree based structures are commonly used for representing point clouds…
Generic event boundary detection aims to localize the generic, taxonomy-free event boundaries that segment videos into chunks. Existing methods typically require video frames to be decoded before feeding into the network, which demands…
One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network. In this paper we propose the concept of PixelMotionCNN (PMCNN)…
Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is…
In the context of long-term video understanding with large multimodal models, many frameworks have been proposed. Although transformer-based visual compressors and memory-augmented approaches are often used to process long videos, they…
This paper tackles an emerging and challenging problem of long video temporal grounding~(VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less…
Text-driven video moment retrieval (VMR) remains challenging due to limited capture of hidden temporal dynamics in untrimmed videos, leading to imprecise grounding in long sequences. Traditional methods rely on natural language queries…
The growing deployment of Large Vision-Language Models (VLMs) raises safety concerns, as adversaries may exploit model vulnerabilities to induce harmful outputs, with targeted black-box adversarial attacks posing a particularly severe…
Blind face video restoration aims to restore high-fidelity details from videos subjected to complex and unknown degradations. This task poses a significant challenge of managing temporal heterogeneity while at the same time maintaining…
Neural networks can be successfully used to improve several modules of advanced video coding schemes. In particular, compression of colour components was shown to greatly benefit from usage of machine learning models, thanks to the design…
This paper focuses on the task of quality enhancement for compressed videos. Although deep network-based video restorers achieve impressive progress, most of the existing methods lack a structured design to optimally leverage the priors…
Joint super-resolution and inverse tone-mapping (SR-ITM) aims to enhance the visual quality of videos that have quality deficiencies in resolution and dynamic range. This problem arises when using 4K high dynamic range (HDR) TVs to watch a…
Vision-Language-Action (VLA) models enable generalist robotic manipulation but suffer from high inference latency. This bottleneck stems from the massive number of visual tokens processed by large language backbones. Existing methods either…
This work presents the first condensation approach for procedural video datasets used in temporal action segmentation. We propose a condensation framework that leverages generative prior learned from the dataset and network inversion to…
The scalability of video understanding models is increasingly limited by the prohibitive storage and computational costs of large-scale video datasets. While data synthesis has improved data efficiency in the image domain, its extension to…
With the remarkable progress in neural P-frame video coding, neural B-frame coding has recently emerged as a critical research direction. However, most existing neural B-frame codecs directly adopt P-frame coding tools without adequately…
Joint compression of point cloud geometry and attributes is essential for efficient 3D data representation. Existing methods often rely on post-hoc recoloring procedures and manually tuned bitrate allocation between geometry and attribute…