Related papers: Spatially Prompted Visual Trajectory Prediction fo…
Embodied agents operating in open environments must translate high-level instructions into grounded, executable behaviors, often requiring coordinated use of both hands. While recent foundation models offer strong semantic reasoning,…
Predicting the next pickup location of individual users is a fundamental problem in intelligent mobility systems, which requires modeling personalized travel behaviors under complex spatiotemporal contexts. Existing methods mainly learn…
Recently, the community has made tremendous progress in developing effective methods for point cloud video understanding that learn from massive amounts of labeled data. However, annotating point cloud videos is usually notoriously…
Manipulating elasto-plastic objects remains a significant challenge due to severe self-occlusion, difficulties of representation, and complicated dynamics. This work proposes a novel framework for elasto-plastic object manipulation with a…
Freight consolidation has significant potential to reduce transportation costs and mitigate congestion and pollution. An effective load consolidation plan relies on carefully chosen consolidation points to ensure alignment with existing…
We study the spatio-temporal prediction problem and introduce a novel point-process-based prediction algorithm. Spatio-temporal prediction is extensively studied in Machine Learning literature due to its critical real-life applications such…
Vision-Language-Action (VLA) models offer significant potential for end-to-end driving, yet their reasoning is often constrained by textual Chains-of-Thought (CoT). This symbolic compression of visual information creates a modality gap…
Mobile manipulation in dynamic environments is challenging due to movable obstacles blocking the robot's path. Traditional methods, which treat navigation and manipulation as separate tasks, often fail in such 'manipulate-to-navigate'…
This paper aims to tackle the interactive behavior prediction task, and proposes a novel Conditional Goal-oriented Trajectory Prediction (CGTP) framework to jointly generate scene-compliant trajectories of two interacting agents. Our CGTP…
Spatial reasoning, the ability to understand spatial relations, causality, and dynamic evolution, is central to human intelligence and essential for real-world applications such as autonomous driving and robotics. Existing studies, however,…
In this paper, we investigate the challenge of spatio-temporal video prediction task, which involves generating future video frames based on historical spatio-temporal observation streams. Existing approaches typically utilize external…
Existing scene text spotting (i.e., end-to-end text detection and recognition) methods rely on costly bounding box annotations (e.g., text-line, word-level, or character-level bounding boxes). For the first time, we demonstrate that…
Existing methods of multi-person video 3D human Pose and Shape Estimation (PSE) typically adopt a two-stage strategy, which first detects human instances in each frame and then performs single-person PSE with temporal model. However, the…
In this work, we focus on the task of procedure planning from instructional videos with text supervision, where a model aims to predict an action sequence to transform the initial visual state into the goal visual state. A critical…
The ability to specify robot commands by a non-expert user is critical for building generalist agents capable of solving a large variety of tasks. One convenient way to specify the intended robot goal is by a video of a person demonstrating…
Visual imitation learning enables robotic agents to acquire skills by observing expert demonstration videos. In the one-shot setting, the agent generates a policy after observing a single expert demonstration without additional fine-tuning.…
Visual observation of objects is essential for many robotic applications, such as object reconstruction and manipulation, navigation, and scene understanding. Machine learning algorithms constitute the state-of-the-art in many fields but…
In this work, we present a new visual prompting method called 3DAxiesPrompts (3DAP) to unleash the capabilities of GPT-4V in performing 3D spatial tasks. Our investigation reveals that while GPT-4V exhibits proficiency in discerning the…
Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them, crucial aspects include guiding the encoder…
This work aims to learn how to perform complex robot manipulation tasks that are composed of several, consecutively executed low-level sub-tasks, given as input a few visual demonstrations of the tasks performed by a person. The sub-tasks…