Related papers: Feature Disentanglement Learning with Switching an…

Most person re-identification (ReID) approaches assume that person images are captured under relatively similar illumination conditions. In reality, long-term person retrieval is common, and person images are often captured under different…

Graph representation of objects and their relations in a scene, known as a scene graph, provides a precise and discernible interface to manipulate a scene by modifying the nodes or the edges in the graph. Although existing works have shown…

Extracting effective and discriminative features is very important for addressing the challenging person re-identification (re-ID) task. Prevailing deep convolutional neural networks (CNNs) usually use high-level features for identifying…

Prevalent nighttime person re-identification (ReID) methods typically combine image relighting and ReID networks in a sequential manner. However, their performance (recognition accuracy) is limited by the quality of relighting images and…

Multimodal image registration is a fundamental task and a prerequisite for downstream cross-modal analysis. Despite recent progress in shared feature extraction and multi-scale architectures, two key limitations remain. First, some methods…

Learning visual representations with interpretable features, i.e., disentangled representations, remains a challenging problem. Existing methods demonstrate some success but are hard to apply to large-scale vision datasets like ImageNet. In…

Visual object tracking remains an active research field in computer vision due to persisting challenges with various problem-specific factors in real-world scenes. Many existing tracking methods based on discriminative correlation filters…

Representations used for Facial Expression Recognition (FER) usually contain expression information along with identity features. In this paper, we propose a novel Disentangled Expression learning-Generative Adversarial Network (DE-GAN)…

As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera. Recently, deep learning-based…

Person re-identification is an important task in video surveillance that aims to associate people across camera views at different locations and time. View variability is always a challenging problem seriously degrading person…

Video anomaly detection is recently formulated as a multiple instance learning task under weak supervision, in which each video is treated as a bag of snippets to be determined whether contains anomalies. Previous efforts mainly focus on…

Learning the generalizable feature representation is critical for few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks…

This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning. In DR-GAN, we introduce two…

Visual perception of a person is easily influenced by many factors such as camera parameters, pose and viewpoint variations. These variations make person Re-Identification (ReID) a challenging problem. Nevertheless, human attributes usually…

Person search is to detect all persons and identify the query persons from detected persons in the image without proposals and bounding boxes, which is different from person re-identification. In this paper, we propose a fusing multi-task…

Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises…

Image classification remains a fundamental yet challenging task in computer vision, particularly when fine-grained feature extraction and background noise suppression are required simultaneously. Conventional convolutional neural networks,…

While Deep Neural Network (DNN) models have provided remarkable advances in machine vision capabilities, their high computational complexity and model sizes present a formidable roadblock to deployment in AIoT-based sensing applications. In…

Vehicle re-identification is an important computer vision task where the objective is to identify a specific vehicle among a set of vehicles seen at various viewpoints. Recent methods based on deep learning utilize a global average pooling…

We propose the cascade attribute learning network (CALNet), which can learn attributes in a control task separately and assemble them together. Our contribution is twofold: first we propose attribute learning in reinforcement learning (RL).…