Related papers: Relational Representation Learning Network for Cro…

Micro-expression recognition (\textbf{MER}) has attracted lots of researchers' attention in a decade. However, occlusion will occur for MER in real-world scenarios. This paper deeply investigates an interesting but unexplored challenging…

Feature extraction plays an important role in visual localization. Unreliable features on dynamic objects or repetitive regions will interfere with feature matching and challenge indoor localization greatly. To address the problem, we…

With the excellent representation capabilities of Pre-Trained Models (PTMs), remarkable progress has been made in non-rehearsal Class-Incremental Learning (CIL) research. However, it remains an extremely challenging task due to three…

Text-video retrieval tasks have seen significant improvements due to the recent development of large-scale vision-language pre-trained models. Traditional methods primarily focus on video representations or cross-modal alignment, while…

Recently, a series of works in computer vision have shown promising results on various image and video understanding tasks using self-attention. However, due to the quadratic computational and memory complexities of self-attention, these…

The multi-plane representation has been highlighted for its fast training and inference across static and dynamic neural radiance fields. This approach constructs relevant features via projection onto learnable grids and interpolating…

Multi-label recognition is a fundamental, and yet is a challenging task in computer vision. Recently, deep learning models have achieved great progress towards learning discriminative features from input images. However, conventional…

Reference-based image super-resolution (RefSR) has shown promising success in recovering high-frequency details by utilizing an external reference image (Ref). In this task, texture details are transferred from the Ref image to the…

Text-based person anomaly retrieval has emerged as a challenging task, with most existing approaches relying on complex deep-learning techniques. This raises a research question: How can the model be optimized to achieve greater…

Modeling the underlying person structure for person re-identification (re-ID) is difficult due to diverse deformable poses, changeable camera views and imperfect person detectors. How to exploit underlying person structure information…

The popularity of self-supervised learning has made it possible to train models without relying on labeled data, which saves expensive annotation costs. However, most existing self-supervised contrastive learning methods often overlook the…

There has recently been significant interest in training reinforcement learning (RL) agents in vision-based environments. This poses many challenges, such as high dimensionality and the potential for observational overfitting through…

Representing urban regions accurately and comprehensively is essential for various urban planning and analysis tasks. Recently, with the expansion of the city, modeling long-range spatial dependencies with multiple data sources plays an…

Lane detection is one of the most important tasks in self-driving. Due to various complex scenarios (e.g., severe occlusion, ambiguous lanes, etc.) and the sparse supervisory signals inherent in lane annotations, lane detection task is…

Current medical image segmentation approaches have limitations in deeply exploring multi-scale information and effectively combining local detail textures with global contextual semantic information. This results in over-segmentation,…

Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. Such a setting severely limits their scalability in real-world…

Personalized fairness in recommendations has been attracting increasing attention from researchers. The existing works often treat a fairness requirement, represented as a collection of sensitive attributes, as a hyper-parameter, and pursue…

Single-frame infrared small target detection is considered to be a challenging task, due to the extreme imbalance between target and background, bounding box regression is extremely sensitive to infrared small target, and target information…

Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image…

In this paper, we propose a deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification. The network takes a pair of raw RGB images as input, and outputs a…