Related papers: Progressive Transformation Learning for Leveraging…
It has been widely recognized that the success of deep learning in image segmentation relies overwhelmingly on a myriad amount of densely annotated training data, which, however, are difficult to obtain due to the tremendous labor and…
Pre-training for Reinforcement Learning (RL) with purely video data is a valuable yet challenging problem. Although in-the-wild videos are readily available and inhere a vast amount of prior world knowledge, the absence of action…
Parameter efficient transfer learning (PETL) aims at making good use of the representation knowledge in the pre-trained large models by fine-tuning a small number of parameters. Recently, taking inspiration from the natural language…
Recognizing a target of interest from the UAVs is much more challenging than the existing object re-identification tasks across multiple city cameras. The images taken by the UAVs usually suffer from significant size difference when…
We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the…
Recent advances in deep learning, particularly neural networks, have significantly impacted a wide range of fields, including the automatic enhancement of underwater images. This paper presents a deep learning-based approach to improving…
Deep learning models have a large number of free parameters that must be estimated by efficient training of the models on a large number of training data samples to increase their generalization performance. In real-world applications, the…
Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated strong few-shot learning capabilities. However, these methods typically learn holistic representations where an image's domain-invariant structure is implicitly…
Most deep learning models are data-driven and the excellent performance is highly dependent on the abundant and diverse datasets. However, it is very hard to obtain and label the datasets of some specific scenes or applications. If we train…
Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per action instance) to train a model to effectively locate action instances within untrimmed…
Tabular data have been playing a mostly important role in diverse real-world fields, such as healthcare, engineering, finance, etc. With the recent success of deep learning, many tabular machine learning (ML) methods based on deep networks…
Vision Transformers (ViTs) excel in semantic segmentation but demand significant computation, posing challenges for deployment on resource-constrained devices. Existing token pruning methods often overlook fundamental visual data…
Recent advances achieved by deep learning models rely on the independent and identically distributed assumption, hindering their applications in real-world scenarios with domain shifts. To tackle this issue, cross-domain learning aims at…
Learning generalizable visual representations across different embodied environments is essential for effective robotic manipulation in real-world scenarios. However, the limited scale and diversity of robot demonstration data pose a…
Temporal action detection (TAD) is challenging, yet fundamental for real-world video applications. Recently, DETR-based models for TAD have been prevailing thanks to their unique benefits. However, transformers demand a huge dataset, and…
Traditional deep learning-based visual imitation learning techniques require a large amount of demonstration data for model training, and the pre-trained models are difficult to adapt to new scenarios. To address these limitations, we…
Vision-and-language pre-training (VLP) models have experienced a surge in popularity recently. By fine-tuning them on specific datasets, significant performance improvements have been observed in various tasks. However, full fine-tuning of…
Change detection, a prominent research area in remote sensing, is pivotal in observing and analyzing surface transformations. Despite significant advancements achieved through deep learning-based methods, executing high-precision change…
Deep Reinforcement Learning (DRL) emerges as a prime solution for Unmanned Aerial Vehicle (UAV) trajectory planning, offering proficiency in navigating high-dimensional spaces, adaptability to dynamic environments, and making sequential…
In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a video-to-video translation task in which the estimated…