Related papers: Video Domain Incremental Learning for Human Action…

This study addresses the Domain-Class Incremental Learning problem, a realistic but challenging continual learning scenario where both the domain distribution and target classes vary across tasks. To handle these diverse tasks, pre-trained…

Policy learning under action constraints plays a central role in ensuring safe behaviors in various robot control and resource allocation applications. In this paper, we study a new problem setting termed Action-Constrained Imitation…

We present a learning algorithm for human activity recognition in videos. Our approach is designed for UAV videos, which are mainly acquired from obliquely placed dynamic cameras that contain a human actor along with background motion.…

Automatic surgical activity recognition enables more intelligent surgical devices and a more efficient workflow. Integration of such technology in new operating rooms has the potential to improve care delivery to patients and decrease…

Catastrophic forgetting makes neural network models unstable when learning visual domains consecutively. The neural network model drifts to catastrophic forgetting-induced low performance of previously learnt domains when training with new…

This study aims to address the problem of multi-domain task incremental learning~(MTIL), which requires that vision-language models~(VLMs) continuously acquire new knowledge while maintaining their inherent zero-shot recognition capability.…

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…

Contemporary Video Instance Segmentation (VIS) methods typically adhere to a pre-train then fine-tune regime, where a segmentation model trained on images is fine-tuned on videos. However, the lack of temporal knowledge in the pre-trained…

Deep neural networks (DNNs) often underperform in real-world, dynamic settings where data distributions change over time. Domain Incremental Learning (DIL) offers a solution by enabling continual model adaptation, with Parameter-Isolation…

A dominant paradigm for learning-based approaches in computer vision is training generic models, such as ResNet for image recognition, or I3D for video understanding, on large datasets and allowing them to discover the optimal…

This study focuses on incremental learning for image classification, exploring how to reduce catastrophic forgetting of all learned knowledge when access to old data is restricted. The challenge lies in balancing plasticity (learning new…

Video understanding has made remarkable progress in recent years, largely driven by advances in deep models and the availability of large-scale annotated datasets. However, existing works typically ignore the inherent domain shifts…

Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing motion and temporal evolution information, particularly in the context of deep convolutional neural networks (CNNs). Compared with optical flow…

The currently leading artificial neural network models of the visual ventral stream - which are derived from a combination of performance optimization and robustification methods - have demonstrated a remarkable degree of behavioral…

In the world where big data reigns and there is plenty of hardware prepared to gather a huge amount of non structured data, data acquisition is no longer a problem. Surveillance cameras are ubiquitous and they capture huge numbers of people…

Imitation from videos often fails when expert demonstrations and learner environments exhibit domain shifts, such as discrepancies in lighting, color, or texture. While visual randomization partially addresses this problem by augmenting…

Video understanding usually requires expensive computation that prohibits its deployment, yet videos contain significant spatiotemporal redundancy that can be exploited. In particular, operating directly on the motion vectors and residuals…

Human activities often occur in specific scene contexts, e.g., playing basketball on a basketball court. Training a model using existing video datasets thus inevitably captures and leverages such bias (instead of using the actual…

We consider the problem of learning multiple tasks in a continual learning setting in which data from different tasks is presented to the learner in a streaming fashion. A key challenge in this setting is the so-called "catastrophic…

Temporal cues in videos provide important information for recognizing actions accurately. However, temporal-discriminative features can hardly be extracted without using an annotated large-scale video action dataset for training. This paper…