Related papers: Attribute Recognition by Joint Recurrent Learning …
Representation learning of pedestrian trajectories transforms variable-length timestamp-coordinate tuples of a trajectory into a fixed-length vector representation that summarizes spatiotemporal characteristics. It is a crucial technique to…
Pedestrian Attribute Recognition (PAR) is one of the indispensable tasks in human-centered research. However, existing datasets neglect different domains (e.g., environments, times, populations, and data sources), only conducting simple…
Autonomous vehicles (AVs) are becoming an indispensable part of future transportation. However, safety challenges and lack of reliability limit their real-world deployment. Towards boosting the appearance of AVs on the roads, the…
Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial…
Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention…
Causal Representation Learning (CRL) aims at identifying high-level causal factors and their relationships from high-dimensional observations, e.g., images. While most CRL works focus on learning causal representations in a single…
Pedestrian detection plays an important role in many applications such as autonomous driving. We propose a method that explores semantic segmentation results as self-attention cues to significantly improve the pedestrian detection…
Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features. However, due to the local perception of the…
Linguistic knowledge has brought great benefits to scene text recognition by providing semantics to refine character sequences. However, since linguistic knowledge has been applied individually on the output sequence, previous methods have…
There are multiple cues in an image which reveal what action a person is performing. For example, a jogger has a pose that is characteristic for jogging, but the scene (e.g. road, trail) and the presence of other joggers can be an…
Rhetorical Role Labeling (RRL) identifies the functional role of each sentence in a document, a key task for discourse understanding in domains such as law and medicine. While hierarchical models capture local dependencies effectively, they…
Pedestrian attributes, e.g., hair length, clothes type and color, locally describe the semantic appearance of a person. Training person re-identification (ReID) algorithms under the supervision of such attributes have proven to be effective…
Designed as extremely deep architectures, deep residual networks which provide a rich visual representation and offer robust convergence behaviors have recently achieved exceptional performance in numerous computer vision problems. Being…
In smart transportation, intelligent systems avoid potential collisions by predicting the intent of traffic agents, especially pedestrians. Pedestrian intent, defined as future action, e.g., start crossing, can be dependent on traffic…
Typical methods for pedestrian detection focus on either tackling mutual occlusions between crowded pedestrians, or dealing with the various scales of pedestrians. Detecting pedestrians with substantial appearance diversities such as…
Detecting tiny objects in a high-resolution video is challenging because the visual information is little and unreliable. Specifically, the challenge includes very low resolution of the objects, MPEG artifacts due to compression and a large…
Conventional representation learning methods learn a universal representation that primarily captures dominant semantics, which may not always align with customized downstream tasks. For instance, in animal habitat analysis, researchers…
Instance-level alignment is widely exploited for person re-identification, e.g. spatial alignment, latent semantic alignment and triplet alignment. This paper probes another feature alignment modality, namely cluster-level feature alignment…
The problem of multi-object tracking is a fundamental computer vision research focus, widely used in public safety, transport, autonomous vehicles, robotics, and other regions involving artificial intelligence. Because of the complexity of…
Anomaly detection in surveillance videos is currently a challenge because of the diversity of possible events. We propose a deep convolutional neural network (CNN) that addresses this problem by learning a correspondence between common…