相关论文: DSANet: Dynamic Segment Aggregation Network for Vi…

3D convolution is powerful for video classification but often computationally expensive, recent studies mainly focus on decomposing it on spatial-temporal and/or channel dimensions. Unfortunately, most approaches fail to achieve a…

Graph Convolution Network (GCN) has been successfully used for 3D human pose estimation in videos. However, it is often built on the fixed human-joint affinity, according to human skeleton. This may reduce adaptation capacity of GCN to…

Dataset distillation (DD) has emerged as a powerful paradigm for dataset compression, enabling the synthesis of compact surrogate datasets that approximate the training utility of large-scale ones. While significant progress has been…

Hierarchical transformers have achieved significant success in medical image segmentation due to their large receptive field and capabilities of effectively leveraging global long-range contextual information. Convolutional neural networks…

Long-form video understanding is essential for various applications such as video retrieval, summarizing, and question answering. Yet, traditional approaches demand substantial computing power and are often bottlenecked by GPU memory. To…

Learning to represent videos is a very challenging task both algorithmically and computationally. Standard video CNN architectures have been designed by directly extending architectures devised for image understanding to include the time…

Recently, self-supervised learning has proved to be effective to learn representations of events suitable for temporal segmentation in image sequences, where events are understood as sets of temporally adjacent images that are semantically…

Existing methods for instance segmentation in videos typically involve multi-stage pipelines that follow the tracking-by-detection paradigm and model a video clip as a sequence of images. Multiple networks are used to detect objects in…

3D semantic scene completion and 2D semantic segmentation are two tightly correlated tasks that are both essential for indoor scene understanding, because they predict the same semantic classes, using positively correlated high-level…

Existing weakly supervised semantic segmentation (WSSS) methods usually utilize the results of pre-trained saliency detection (SD) models without explicitly modeling the connections between the two tasks, which is not the most efficient…

Scene flow estimation, which predicts the 3D motion of scene points from point clouds, is a core task in autonomous driving and many other 3D vision applications. Existing methods either suffer from structure distortion due to ignorance of…

Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them into the networks. Our paper proposes a novel-and-simple…

This paper addresses fast semantic segmentation on video.Video segmentation often calls for real-time, or even fasterthan real-time, processing. One common recipe for conserving computation arising from feature extraction is to propagate…

Dynamic Scene Graph Generation (DSGG) models how object relations evolve over time in videos. However, existing methods are trained only on annotated object pairs and lack guidance for non-related pairs, making it difficult to identify…

Video classification researches that have recently attracted attention are the fields of temporal modeling and 3D efficient architecture. However, the temporal modeling methods are not efficient or the 3D efficient architecture is less…

Video objection detection (VID) has been a rising research direction in recent years. A central issue of VID is the appearance degradation of video frames caused by fast motion. This problem is essentially ill-posed for a single frame.…

Point cloud segmentation is one of the most important tasks in computer vision with widespread scientific, industrial, and commercial applications. The research thereof has resulted in many breakthroughs in 3D object and scene…

Medical image segmentation, particularly in multi-domain scenarios, requires precise preservation of anatomical structures across diverse representations. While deep learning has advanced this field, existing models often struggle with…

Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR). Due to the characteristics of video tasks, it is very important that motion information among frames should be well…

This paper proposes a new framework for semantic segmentation of objects in videos. We address the label inconsistency problem of deep convolutional neural networks (DCNNs) by exploiting the fact that videos have multiple frames; in a few…