Related papers: Weakly and Self-Supervised Class-Agnostic Motion P…

Most existing crowd counting methods require object location-level annotation, i.e., placing a dot at the center of an object. While being simpler than the bounding-box or pixel-level annotation, obtaining this annotation is still…

In recent years, computer vision has transformed fields such as medical imaging, object recognition, and geospatial analytics. One of the fundamental tasks in computer vision is semantic image segmentation, which is vital for precise object…

Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled…

3D semantic scene understanding tasks have achieved great success with the emergence of deep learning, but often require a huge amount of manually annotated training data. To alleviate the annotation cost, we propose the first…

Driving is challenging in conditions like night, rain, and snow. Lack of good labeled datasets has hampered progress in scene understanding under such conditions. Unsupervised Domain Adaptation (UDA) using large labeled clear-day datasets…

Change detection from traditional \added{2D} optical images has limited capability to model the changes in the height or shape of objects. Change detection using 3D point cloud \added{from photogrammetry or LiDAR surveying} can fill this…

Predicting the future motion of surrounding agents is essential for autonomous vehicles (AVs) to operate safely in dynamic, human-robot-mixed environments. However, the scarcity of large-scale driving datasets has hindered the development…

Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak supervision, while efficient annotation strategies remain largely…

State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of…

Modern deep learning models require large amounts of accurately annotated data, which is often difficult to satisfy. Hence, weakly supervised tasks, including weakly supervised object localization~(WSOL) and detection~(WSOD), have recently…

Self-supervised prediction is a powerful mechanism to learn representations that capture the underlying structure of the data. Despite recent progress, the self-supervised video prediction task is still challenging. One of the critical…

Different from general object detection, moving infrared small target detection faces huge challenges due to tiny target size and weak background contrast.Currently, most existing methods are fully-supervised, heavily relying on a large…

Diagnostic and intervention methodologies for skill assessment of autism typically requires a clinician repetitively initiating several stimuli and recording the child's response. In this paper, we propose to automate the response…

Reliance on vast annotations to achieve leading performance severely restricts the practicality of large-scale point cloud semantic segmentation. For the purpose of reducing data annotation costs, effective labeling schemes are developed…

Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based…

Weakly-supervised action segmentation is a task of learning to partition a long video into several action segments, where training videos are only accompanied by transcripts (ordered list of actions). Most of existing methods need to infer…

In one-class-learning tasks, only the normal case (foreground) can be modeled with data, whereas the variation of all possible anomalies is too erratic to be described by samples. Thus, due to the lack of representative data, the…

Temporal Activity Detection aims to predict activity classes per frame, in contrast to video-level predictions in Activity Classification (i.e., Activity Recognition). Due to the expensive frame-level annotations required for detection, the…

One major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses. In this paper, we address this challenge by proposing a…

Understanding human motion is crucial for accurate pedestrian trajectory prediction. Conventional methods typically rely on supervised learning, where ground-truth labels are directly optimized against predicted trajectories. This amplifies…