Related papers: Semi-TCL: Semi-Supervised Track Contrastive Repres…
We investigate contrastive learning in the federated setting through the lens of SimCLR and multi-view mutual information maximization. In doing so, we uncover a connection between contrastive representation learning and user verification;…
Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and…
Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this…
Scene text recognition (STR) is a challenging task that requires large-scale annotated data for training. However, collecting and labeling real text images is expensive and time-consuming, which limits the availability of real data.…
Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…
Single object tracking aims to locate the target object in a video sequence according to the state specified by different modal references, including the initial bounding box (BBOX), natural language (NL), or both (NL+BBOX). Due to the gap…
Multi-object tracking (MOT) aims to associate target objects across video frames in order to obtain entire moving trajectories. With the advancement of deep neural networks and the increasing demand for intelligent video analysis, MOT has…
Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable…
We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…
To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…
This paper proposes an online visual multi-object tracking algorithm using a top-down Bayesian formulation that seamlessly integrates state estimation, track management, clutter rejection, occlusion and mis-detection handling into a single…
Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision. In this paper, we found…
We introduce a novel framework to track multiple objects in overhead camera videos for airport checkpoint security scenarios where targets correspond to passengers and their baggage items. We propose a Self-Supervised Learning (SSL)…
The presence of objects that are confusingly similar to the tracked target, poses a fundamental challenge in appearance-based visual tracking. Such distractor objects are easily misclassified as the target itself, leading to eventual…
Visual recognition tasks are often limited to dealing with a small subset of classes simply because the labels for the remaining classes are unavailable. We are interested in identifying novel concepts in a dataset through representation…
This paper addresses the problem of online tracking and classification of multiple objects in an image sequence. Our proposed solution is to first track all objects in the scene without relying on object-specific prior knowledge, which in…
To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…
Query-based video grounding is an important yet challenging task in video understanding, which aims to localize the target segment in an untrimmed video according to a sentence query. Most previous works achieve significant progress by…
Traditional supervised learning methods are hitting a bottleneck because of their dependency on expensive manually labeled data and their weaknesses such as limited generalization ability and vulnerability to adversarial attacks. A…
A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning is aimed towards addressing this challenge. However, there is a gap between existing…