Video try-on is challenging and has not been well tackled in previous works. The main obstacle lies in preserving the clothing details and modeling the coherent motions simultaneously. Faced with those difficulties, we address video try-on by proposing a ...

Recent human matting methods typically suffer from two drawbacks: 1) high computation overhead caused by multiple stages, and 2) limited practical application due to the need for auxiliary guidance (e.g., trimap, mask, or background). To address ...

Few-shot classification (FSC) is a highly challenging task, as only a small number of labeled samples are available when identifying new categories. Distance metric learning-based methods have emerged as a prominent approach to FSC, which ...

• A plug-and-play query-centric distance modulator for distance metric learning-based FSC methods.
• Weight generation through data inconsistency within each channel from different classes.
• Decoupled from the process of feature ...

Few-shot action recognition is a challenging but practical problem aiming to learn a model that can be easily adapted to identify new action categories with only a few labeled samples. However, existing attempts still suffer from two drawbacks: (...

• A new temporal coherence regularization on videos is proposed.
• Capturing the intra- and inter-relations inside the episodic task.
• Reformulating the query-support metric as a set matching problem.

Pedestrian reidentification (ReID) is a challenging task that involves identifying and retrieving specific pedestrians across different cameras and scenes. This problem has significant implications for security surveillance, and has thus received ...

Tone mapping aims to convert high dynamic range (HDR) images to low dynamic range (LDR) representations, a critical task in the camera imaging pipeline. In recent years, 3-Dimensional Look-Up Table (3D LUT) based methods have gained attention due to ...

Recently, deep learning-based methods have been successfully applied to the field of exposure correction. However, most of the existing methods treat different locations of an image in the same way, ignoring the inhomogeneous recovery difficulty and ...

Image matting aims to estimate the opacity of foreground objects in order to accurately extract them from the background. Existing methods are only concerned with RGB features to obtain alpha mattes, limiting the perception of local tiny details. ...

Portrait matting is a challenging computer vision task that aims to estimate the per-pixel opacity of the foreground human regions. To produce high-quality alpha mattes, the majority of available methods employ a user-supplied trimap as an ...

With the aim of retrieving high-quality images from corrupted versions, image restoration meets the extensive demand of application scenarios. State-of-the-art methods solve this problem by means of designing convolution blocks in multistage ...

Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under-explored on the challenging few-shot action recognition (FSAR) task. In ...

Deep learning-based methods for low-light image enhancement have achieved remarkable success. However, the requirement of enormous paired real data limits the generality of these models. Although there have been a few attempts in training low-...

Natural untrimmed videos provide rich visual content for self-supervised learning. Yet most previous efforts to learn spatio-temporal representations rely on manually trimmed videos, such as Kinetics dataset (Carreira and Zisserman 2017), resulting in ...

Current few-shot action recognition approaches have achieved impressive performance using only a few labeled examples. However, they usually assume the base (train) and target (test) videos typically come from the same domain, which may limit ...

• Few-shot action recognition methods perform poorly in cross-domain situations.
• Self-supervised learning can alleviate domain shift.
• Temporal modeling is important in the cross-domain few-shot action setting.
• This is the first ...

Current semantic segmentation methods mainly focus on modeling the context of the global image to obtain high-quality segmentation results. However, they ignore the role of local image patches, which contain complementary and effective context ...

Few-shot classification (FSC), which aims to identify novel classes in the presence of a few labeled samples, has drawn vast attention in recent years. One of the representative few-shot classification methods is model-agnostic meta-learning (MAML), which ...

Since the fully convolutional network has achieved great success in semantic segmentation, lots of works have been proposed to extract discriminative pixel representations. However, the authors observe that existing methods still suffer from two ...

Person search aims at localizing and recognizing query persons from raw video frames, which is a combination of two sub-tasks, i.e., pedestrian detection and person re-identification. The dominant fashion is termed as the one-step person search that ...

Most existing methods for RGB hand pose estimation use root-relative 3D coordinates for supervision. However, such supervision neglects the distance between the camera and the object (i.e., the hand). The camera distance is especially ...

Display Omitted

• The same hand pose projected different 2D shapes due to the camera distance.
• ...

Standard approaches for video action recognition usually operate on full input videos, which is inefficient due to the widespread spatio-temporal redundancy in videos. The recent progress in masked video modelling, specifically VideoMAE, has shown the ...