Related papers: Focus On Details: Online Multi-object Tracking wit…
Fine-grained image recognition is challenging because discriminative clues are usually fragmented, whether from a single image or multiple images. Despite their significant improvements, most existing methods still focus on the most…
Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space. Existing deep learning methods follow a hierarchical feature extraction paradigm in…
Fine-grained image recognition has been a hot research topic in computer vision due to its various applications. The-state-of-the-art is the part/region-based approaches that first localize discriminative parts/regions, and then learn their…
Fine-grained action recognition (FGAR) aims to identify subtle and distinctive differences among fine-grained action categories. However, current recognition methods often capture coarse-grained motion patterns but struggle to identify…
Recently, masked image modeling (MIM), which learns visual representations by reconstructing the masked patches of an image, has dominated self-supervised learning in computer vision. However, the pre-training of MIM always takes massive…
Multi-Person Tracking (MPT) is often addressed within the detection-to-association paradigm. In such approaches, human detections are first extracted in every frame and person trajectories are then recovered by a procedure of data…
Part-level representations are important for robust person re-identification (ReID), but in practice feature quality suffers due to the body part misalignment problem. In this paper, we present a robust, compact, and easy-to-use method…
Despite significant success of deep learning in object detection tasks, the standard training of deep neural networks requires access to a substantial quantity of annotated images across all classes. Data annotation is an arduous and…
Recently, heatmap regression has been widely explored in facial landmark detection and obtained remarkable performance. However, most of the existing heatmap regression-based facial landmark detection methods neglect to explore the…
The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing…
Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative, fine-grained dimension by integrating patch-level discrimination into these methodologies. This…
Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…
Graph contrastive learning defines a contrastive task to pull similar instances close and push dissimilar instances away. It learns discriminative node embeddings without supervised labels, which has aroused increasing attention in the past…
Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the…
Multi-Instance Generation has advanced significantly in spatial placement and attribute binding. However, existing approaches still face challenges in fine-grained semantic understanding, particularly when dealing with complex textual…
As fine-grained visual classification (FGVC) being developed for decades, great works related have exposed a key direction -- finding discriminative local regions and revealing subtle differences. However, unlike identifying visual contents…
Discriminative Correlation Filters based tracking algorithms exploiting conventional handcrafted features have achieved impressive results both in terms of accuracy and robustness. Template handcrafted features have shown excellent…
Multiple Object Tracking (MOT) plays an important role in solving many fundamental problems in video analysis in computer vision. Most MOT methods employ two steps: Object Detection and Data Association. The first step detects objects of…
Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking because they require very long training time and a large number of…
The aim of multiple object tracking (MOT) is to detect all objects in a video and bind them into multiple trajectories. Generally, this process is carried out in two steps: detecting objects and associating them across frames based on…