Related papers: RPT++: Customized Feature Representation for Siame…
Point cloud-based 3D object tracking is an important task in autonomous driving. Though great advances regarding Siamese-based 3D tracking have been made recently, it remains challenging to learn the correlation between the template and…
Polarization images provide rich physical information that is fundamentally absent from standard RGB images, benefiting a wide range of computer vision applications such as reflection separation and material classification. However, the…
Pedestrian attribute recognition (PAR) is a fundamental perception task in intelligent transportation and security. To tackle this fine-grained task, most existing methods focus on extracting regional features to enrich attribute…
Automated characterization of spatial data is a kind of critical geographical intelligence. As an emerging technique for characterization, Spatial Representation Learning (SRL) uses deep neural networks (DNNs) to learn non-linear embedded…
We propose an object tracking method, SFTrack++, that smoothly learns to preserve the tracked object consistency over space and time dimensions by taking a spectral clustering approach over the graph of pixels from the video, using a fast…
Inferring the 6DoF pose of an object from a single RGB image is an important but challenging task, especially under heavy occlusion. While recent approaches improve upon the two stage approaches by training an end-to-end pipeline, they do…
To advance the field of autonomous robotics, particularly in object search tasks within unexplored environments, we introduce a novel framework centered around the Probable Object Location (POLo) score. Utilizing a 3D object probability…
Employing part-level features for pedestrian image description offers fine-grained information and has been verified as beneficial for person retrieval in very recent literature. A prerequisite of part discovery is that each part should be…
This paper introduces ROI-Packing, an efficient image compression method tailored specifically for machine vision. By prioritizing regions of interest (ROI) critical to end-task accuracy and packing them efficiently while discarding less…
A main challenge of Visual-Language Tracking (VLT) is the misalignment between visual inputs and language descriptions caused by target movement. Previous trackers have explored many effective feature modification methods to preserve more…
Existing point cloud feature learning networks often incorporate sequences of sampling, neighborhood grouping, neighborhood-wise feature learning, and feature aggregation to learn high-semantic point features that represent the global…
Polarimetric imaging enables advanced vision applications such as normal estimation and de-reflection by capturing unique surface-material interactions. However, existing applications (alternatively called downstream tasks) rely on datasets…
Recently a category of tracking methods based on "tracking-by-detection" is widely used in visual tracking problem. Most of these methods update the classifier online using the samples generated by the tracker to handle the appearance…
Maintaining the identity of multiple objects in real-time video is a challenging task, as it is not always feasible to run a detector on every frame. Thus, motion estimation systems are often employed, which either do not scale well with…
Data association-based multiple object tracking (MOT) involves multiple separated modules processed or optimized differently, which results in complex method design and requires non-trivial tuning of parameters. In this paper, we present an…
Visual object tracking is an important computer vision problem with numerous real-world applications including human-computer interaction, autonomous vehicles, robotics, motion-based recognition, video indexing, surveillance and security.…
Recently, correlation filters have demonstrated the excellent performance in visual tracking. However, the base training sample region is larger than the object region,including the Interference Region(IR). The IRs in training samples from…
Feature learning on point clouds has shown great promise, with the introduction of effective and generalizable deep learning frameworks such as pointnet++. Thus far, however, point features have been abstracted in an independent and…
Pooling is needed to aggregate frame-level features into utterance-level representations for speaker modeling. Given the success of statistics-based pooling methods, we hypothesize that speaker characteristics are well represented in the…
Sparse representation has recently been successfully applied in visual tracking. It utilizes a set of templates to represent target candidates and find the best one with the minimum reconstruction error as the tracking result. In this…