Related papers: Learning-based Prediction and Uplink Retransmissio…
Reinforcement learning can enable robots to navigate to distant goals while optimizing user-specified reward functions, including preferences for following lanes, staying on paved paths, or avoiding freshly mowed grass. However, online…
Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random…
In this paper, we demonstrate how to learn the objective function of a decision-maker while only observing the problem input data and the decision-maker's corresponding decisions over multiple rounds. We present exact algorithms for this…
Modern recommender systems aim to improve user experience. As reinforcement learning (RL) naturally fits this objective -- maximizing an user's reward per session -- it has become an emerging topic in recommender systems. Developing…
Recent advances in deep learning have significantly improved performance of video prediction. However, state-of-the-art methods still suffer from blurriness and distortions in their future predictions, especially when there are large…
Understanding the 3D world without supervision is currently a major challenge in computer vision as the annotations required to supervise deep networks for tasks in this domain are expensive to obtain on a large scale. In this paper, we…
The study of vision-and-language navigation (VLN) has typically relied on expert trajectories, which may not always be available in real-world situations due to the significant effort required to collect them. On the other hand, existing…
In this paper, we propose a visual tracker based on a metric-weighted linear representation of appearance. In order to capture the interdependence of different feature dimensions, we develop two online distance metric learning methods using…
Machine-learning-based prediction of future wireless link quality is an emerging technique that can potentially improve the reliability of wireless communications, especially at higher frequencies (e.g., millimeter-wave and terahertz…
Vision-and-language navigation (VLN) is a challenging task that requires an agent to navigate in real-world environments by understanding natural language instructions and visual information received in real-time. Prior works have…
In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultaneously prevent catastrophic forgetting and underfitting on…
Offline reinforcement learning (RL) aims to learn a policy from a static dataset without further interactions with the environment. Collecting sufficiently large datasets for offline RL is exhausting since this data collection requires…
Self-supervised VO methods have shown great success in jointly estimating camera pose and depth from videos. However, like most data-driven methods, existing VO networks suffer from a notable decrease in performance when confronted with…
Compared with short-term tracking, the long-term tracking task requires determining the tracked object is present or absent, and then estimating the accurate bounding box if present or conducting image-wide re-detection if absent. Until…
Deep neural networks (DNNs) are often trained on the premise that the complete training data set is provided ahead of time. However, in real-world scenarios, data often arrive in chunks over time. This leads to important considerations…
While 5G New Radio (NR) networks offer significant uplink throughput improvements, these gains are primarily realized when User Equipment (UE) connects to high-frequency millimeter wave (mmWave) bands. The growing demand for…
Nowadays, panoramic images can be easily obtained by panoramic cameras. However, when the panoramic camera orientation is tilted, a non-upright panoramic image will be captured. Existing upright adjustment models focus on how to estimate…
Selection is one of the fundamental user interactions in virtual reality (VR) and 3D user interaction, and raycasting has been one of the most popular object selection techniques in VR. However, the selection of small or distant objects…
We propose a new online learning model for learning with preference feedback. The model is especially suited for applications like web search and recommender systems, where preference data is readily available from implicit user feedback…
We propose an approach to predict the 3D shape and pose for the objects present in a scene. Existing learning based methods that pursue this goal make independent predictions per object, and do not leverage the relationships amongst them.…