Related papers: AdaTracker: Learning Adaptive In-Context Policy fo…

Cross-embodiment learning seeks to build generalist robots that operate across diverse morphologies, but differences in action spaces and kinematics hinder data sharing and policy transfer. This raises a central question: Is there any…

Existing FPV object tracking methods heavily rely on handcrafted modular pipelines, which incur high onboard computation and cumulative errors. While learning-based approaches have mitigated computational delays, most still generate only…

In the last decade many different algorithms have been proposed to track a generic object in videos. Their execution on recent large-scale video datasets can produce a great amount of various tracking behaviours. New trends in Reinforcement…

Humans are excellent at understanding language and vision to accomplish a wide range of tasks. In contrast, creating general instruction-following embodied agents remains a difficult challenge. Prior work that uses pure language-only models…

We present a scalable framework for cross-embodiment humanoid robot control by learning a shared latent representation that unifies motion across humans and diverse humanoid platforms, including single-arm, dual-arm, and legged humanoid…

In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder…

Eye-tracking is a vital technology for human-computer interaction, especially in wearable devices such as AR, VR, and XR. The realization of high-speed and high-precision eye-tracking using frame-based image sensors is constrained by their…

Video anomalies often depend on contextual information available and temporal evolution. Non-anomalous action in one context can be anomalous in some other context. Most anomaly detectors, however, do not notice this type of context, which…

Robotic imitation learning has advanced from solving static tasks to addressing dynamic interaction scenarios, but testing and evaluation remain costly and challenging due to the need for real-time interaction with dynamic environments. We…

Efficiently modeling spatio-temporal relations of objects is a key challenge in visual object tracking (VOT). Existing methods track by appearance-based similarity or long-term relation modeling, resulting in rich temporal contexts between…

We explore how to enhance next-token prediction models to perform in-context imitation learning on a real robot, where the robot executes new tasks by interpreting contextual information provided during the input phase, without updating its…

Humanoid robots are envisioned to adapt demonstrated motions to diverse real-world conditions while accurately preserving motion patterns. Existing motion prior approaches enable well adaptability with a few motions but often sacrifice…

Vision-language tracking aims to locate the target object in the video sequence using a template patch and a language description provided in the initial frame. To achieve robust tracking, especially in complex long-term scenarios that…

In-context imitation learning enables robots to adapt to new tasks from a small number of demonstrations without additional training. However, existing approaches typically condition only on state-action trajectories and lack explicit…

Refining visual representations by eliminating their internal feature-level redundancy is crucial for simultaneously optimizing the performance and computational cost of models in visual tracking. To enhance their performance, many…

Multimodal semantic cues, such as textual descriptions, have shown strong potential in enhancing target perception for tracking. However, existing methods rely on static textual descriptions from large language models, which lack…

We introduce Diff-Tracker, a novel approach for the challenging unsupervised visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea is to leverage the rich knowledge encapsulated within the pre-trained…

Visual multi-object tracking has the potential to accelerate many forms of quantitative analyses, especially in research communities investigating the motion, behavior, or social interactions within groups of animals. Despite its potential…

VOT remains a fundamental yet challenging task in computer vision due to dynamic appearance changes, occlusions, and background clutter. Traditional trackers, relying primarily on visual cues, often struggle in such complex scenarios.…

Embodied visual tracking is a fundamental skill in Embodied AI, enabling an agent to follow a specific target in dynamic environments using only egocentric vision. This task is inherently challenging as it requires both accurate target…