Related papers: Beyond Domain Randomization: Event-Inspired Percep…

Understanding how the predictions of deep learning models are formed during the training process is crucial to improve model performance and fix model defects, especially when we need to investigate nontrivial training strategies such as…

Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks. In such framework, besides the regular ConvNets responsible for RGB frame inputs, a…

Deep learning models heavily rely on large scale annotated datasets for training. Unfortunately, datasets cannot capture the infinite variability of the real world, thus neural networks are inherently limited by the restricted visual and…

Deploying machine learning algorithms for robot tasks in real-world applications presents a core challenge: overcoming the domain gap between the training and the deployment environment. This is particularly difficult for visuomotor…

Keystroke inference attacks are a form of side-channel attacks in which an attacker leverages various techniques to recover a user's keystrokes as she inputs information into some display (e.g., while sending a text message or entering her…

Deep reinforcement learning (DRL) agents are often sensitive to visual changes that were unseen in their training environments. To address this problem, we leverage the sequential nature of RL to learn robust representations that encode…

Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to…

In video understanding, most cross-modal knowledge distillation (KD) methods are tailored for classification tasks, focusing on the discriminative representation of the trimmed videos. However, action detection requires not only…

Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Visual model-based RL methods typically encode image observations into low-dimensional representations in a manner that does not eliminate redundant information. This leaves them susceptible to spurious variations -- changes in…

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal. Expert demonstrations provided by humans, however, often show significant variability due to latent factors that are typically not…

Though deep reinforcement learning agents have achieved unprecedented success in recent years, their learned policies can be brittle, failing to generalize to even slight modifications of their environments or unfamiliar situations. The…

One significant factor we expect the video representation learning to capture, especially in contrast with the image representation learning, is the object motion. However, we found that in the current mainstream video datasets, some action…

Event-cameras have emerged as a revolutionary technology with a high temporal resolution that far surpasses standard active pixel cameras. This technology draws biological inspiration from photoreceptors and the initial retinal synapse.…

We propose to harness the potential of simulation for the semantic segmentation of real-world self-driving scenes in a domain generalization fashion. The segmentation network is trained without any data of target domains and tested on the…

We address the challenging problem of learning motion representations using deep models for video recognition. To this end, we make use of attention modules that learn to highlight regions in the video and aggregate features for…

Scene recognition is one of the basic problems in computer vision research with extensive applications in robotics. When available, depth images provide helpful geometric cues that complement the RGB texture information and help to identify…

Modeling Neural Radiance Fields for fast-moving deformable objects from visual data alone is a challenging problem. A major issue arises due to the high deformation and low acquisition rates. To address this problem, we propose to use event…

Traditional approaches for analyzing RGB frames are capable of providing a fine-grained understanding of a face from different angles by inferring emotions, poses, shapes, landmarks. However, when it comes to subtle movements standard RGB…