17 accepted papers
Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from human feedback has been successful in aligning agents with human intent, acquiring high-quality feedback is costly and…
Offline reinforcement learning (RL) provides a powerful framework for training robotic agents using pre-collected, suboptimal datasets, eliminating the need for costly, time-consuming, and potentially hazardous online interactions. This is particularly useful in safety-critical real-world applicatio
In offline reinforcement learning (RL), learning from fixed datasets presents a promising solution for domains where real-time interaction with the environment is expensive or risky. However, designing dense reward signals for offline dataset requires significant human effort and domain expertise. R…
Recent research highlights the potential of multi-modal foundation models in tackling complex decision-making challenges. However, their large parameters make real-world deployment resource-intensive and often impractical for constrained systems. Reinforcement learning (RL) shows promise for task-sp…
Recent work in offline reinforcement learning (RL) has demonstrated the effectiveness of formulating decision-making as return-conditioned supervised learning. Notably, the decision transformer (DT) architecture has shown promise across various domains. However, despite its initial success, DTs have…
While generative modeling on multimodal image-text data has been actively developed with large-scale paired datasets, there have been limited attempts to generate both image and text data by a single model rather than a generation of one fixed modality conditioned on the other modality. In this pape…
Episodic count has been widely used to design a simple yet effective intrinsic motivation for reinforcement learning with a sparse reward. However, the use of episodic count in a high-dimensional state space as well as over a long episode time requires a thorough state compression and fast hashing,…
We consider the problem of online and real-time registration of partial point clouds obtained from an unseen real-world rigid object without knowing its 3D model. The point cloud is partial as it is obtained by a depth sensor capturing only the visible part of the object from a certain viewpoint. It…
Data augmentation can impact the generalization performance of an image classification model in a significant way. However, it is currently conducted on the basis of trial and error, and its impact on the generalization performance cannot be predicted during training. This paper considers an influen…
Channel-gain cartography relies on sensor measurements to construct maps providing the attenuation profile between arbitrary transmitter-receiver locations. State-of-the-art on this subject includes tomography-based approaches, where shadowing effects are modeled by the weighted integral of a spatia…
In this paper, we introduce a new problem of manipulating a given video by inserting other videos into it. Our main task is, given an object video and a scene video, to insert the object video at a user-specified location in the scene video so that the resulting video looks realistic. We aim to hand…
Channel gain cartography relies on sensor measurements to construct maps providing the attenuation profile between arbitrary transmitter-receiver locations. Existing approaches capitalize on tomographic models, where shadowing is the weighted integral of a spatial loss field (SLF) depending on the p…
Learning to insert an object instance into an image in a semantically coherent manner is a challenging and interesting problem. Solving it requires (a) determining a location to place an object in the scene and (b) determining its appearance at the location. Such an object insertion model can potent…
We introduce a new problem of generating an image based on a small number of key local patches without any geometric prior. In this work, key local patches are defined as informative regions of the target object or scene. This is a challenging problem since it requires generating realistic images an…
In this paper, we propose a face alignment method that uses cascade Gaussian process regression trees (cGPRT) constructed by combining Gaussian process regression trees (GPRT) in a cascade stage-wise manner. Here, GPRT is a Gaussian process with a kernel defined by a set of trees. The kernel measure…
This paper examines a novel binary feature referred to as the Local Hybrid Patterns (LHP) that is generated by mixing highly discriminative bits of the binary local pattern features (BLPFs) such as the Local Binary Patterns (LBP), Local Gradient Patterns (LGP), and Mean LBP (MLBP). Starting with the…
In this paper, we consider the problem of estimating the gaze direction of a person from a low-resolution image. Under this condition, reliably extracting facial features is very difficult. We propose a novel head pose estimation algorithm based on compressive sensing. Head image patches are mapp…