Related papers: A Solution to Co-occurrence Bias: Attributes Disen…
Pedestrian attribute recognition has received increasing attention due to its important role in video surveillance applications. However, most existing methods are designed for a fixed set of attributes. They are unable to handle the…
In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a shared representation…
Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…
Skeleton-based human action recognition has recently drawn increasing attentions with the availability of large-scale skeleton datasets. The most crucial factors for this task lie in two aspects: the intra-frame representation for joint…
Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount of training data or its limited feature coverage. This can lead to RL agents encoding these misleading…
Existing models often leverage co-occurrences between objects and their context to improve recognition accuracy. However, strongly relying on context risks a model's generalizability, especially when typical co-occurrence patterns are…
Recognising semantic pedestrian attributes in surveillance images is a challenging task for computer vision, particularly when the imaging quality is poor with complex background clutter and uncontrolled viewing conditions, and the number…
We consider the disentanglement of the representations of the relevant attributes of the data (content) from all other factors of variations (style) using Variational Autoencoders. Some recent works addressed this problem by utilizing…
Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models. Existing methods mostly focus on regular entangled representations to discriminate in-distribution (ID) and OOD data, neglecting the rich…
State-of-the-art methods treat pedestrian attribute recognition as a multi-label image classification problem. The location information of person attributes is usually eliminated or simply encoded in the rigid splitting of whole body in…
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…
Learning to recognize pedestrian attributes at far distance is a challenging problem in visual surveillance since face and body close-shots are hardly available; instead, only far-view image frames of pedestrian are given. In this study, we…
Learning to predict multiple attributes of a pedestrian is a multi-task learning problem. To share feature representation between two individual task networks, conventional methods like Cross-Stitch and Sluice network learn a linear…
This paper focuses on the problem of decentralized pedestrian tracking using a sensor network. Traditional works on pedestrian tracking usually use a centralized framework, which becomes less practical for robotic applications due to…
Rooting in the scarcity of most attributes, realistic pedestrian attribute datasets exhibit unduly skewed data distribution, from which two types of model failures are delivered: (1) label imbalance: model predictions lean greatly towards…
The automatic characterization of pedestrians in surveillance footage is a tough challenge, particularly when the data is extremely diverse with cluttered backgrounds, and subjects are captured from varying distances, under multiple poses,…
Correlations between factors of variation are prevalent in real-world data. Exploiting such correlations may increase predictive performance on noisy data; however, often correlations are not robust (e.g., they may change between domains,…
Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, but previous representation learning methods use tightly…
Image downscaling is one of the widely used operations in image processing and computer graphics. It was recently demonstrated in the literature that kernel-based convolutional filters could be modified to develop efficient image…
In this paper, we first tackle the problem of pedestrian attribute recognition by video-based approach. The challenge mainly lies in spatial and temporal modeling and how to integrating them for effective and dynamic pedestrian…