Related papers: FALCON: Future-Aware Learning with Contextual Obje…
Integral field spectrographs are major instruments to study the mechanisms involved in the formation and the evolution of early galaxies. When combined with multi-object spectroscopy, those spectrographs can behave as machines used to…
Autonomous inspection in hazardous environments requires AI agents that can interpret high-level goals and execute precise control. A key capability for such agents is spatial grounding, for example when a drone must center a detected…
Autonomous aerial scanning of target structures is crucial for practical applications, requiring online adaptation to unknown obstacles during flight. Existing methods largely emphasize collision avoidance and efficiency, but overlook…
Open-Vocabulary Temporal Action Detection (OV-TAD) aims to localize and classify action segments of unseen categories in untrimmed videos, where effective alignment between action semantics and video representations is critical for accurate…
Large-scale vision foundation models such as DINOv2 boast impressive performances by leveraging massive architectures and training datasets. But numerous scenarios require practitioners to reproduce those pre-training solutions, such as on…
Action recognition has been a widely studied topic with a heavy focus on supervised learning involving sufficient labeled videos. However, the problem of cross-domain action recognition, where training and testing videos are drawn from…
Deep-predictive-coding networks (DPCNs) are hierarchical, generative models. They rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial…
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…
Foreground segmentation is a fundamental task in computer vision, encompassing various subdivision tasks. Previous research has typically designed task-specific architectures for each task, leading to a lack of unification. Moreover, they…
Confidence estimation for Vision-Language-Action (VLA) models is essential for robots to perform manipulation tasks in the open world, providing crucial signals for risk-sensitive decision-making and failure anticipation. Existing…
Autonomous navigation and path-planning around non-cooperative space objects is an enabling technology for on-orbit servicing and space debris removal systems. The navigation task includes the determination of target object motion, the…
Fluoroscopy is critical for real-time X-ray visualization in medical imaging. However, low-dose images are compromised by noise, potentially affecting diagnostic accuracy. Noise reduction is crucial for maintaining image quality, especially…
The rapid evolution of generative AI has increased the threat of realistic audio-visual deepfakes, demanding robust detection methods. Existing solutions primarily address unimodal (audio or visual) forgeries but struggle with multimodal…
Leveraging vast amounts of unlabeled internet video data for embodied AI is currently bottlenecked by the lack of action labels and the presence of action-correlated visual distractors. Although recent latent action policy optimization…
Despite recent advancements in computer vision research, object detection in aerial images still suffers from several challenges. One primary challenge to be mitigated is the presence of multiple types of variation in aerial images, for…
Anticipating actions and objects before they start or appear is a difficult problem in computer vision with several real-world applications. This task is challenging partly because it requires leveraging extensive knowledge of the world…
The field of physics-based animation is gaining importance due to the increasing demand for realism in video games and films, and has recently seen wide adoption of data-driven techniques, such as deep reinforcement learning (RL), which…
It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…
Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images like those in ImageNet and ignores the correlation among the…
Multi-robot target tracking is a fundamental problem that requires coordinated monitoring of dynamic entities in applications such as precision agriculture, environmental monitoring, disaster response, and security surveillance. While…