Related papers: Multi-Stage Reinforcement Learning For Object Dete…

Multi-shot pedestrian re-identification problem is at the core of surveillance video analysis. It matches two tracks of pedestrians from different cameras. In contrary to existing works that aggregate single frames features by time series…

Close and precise placement of irregularly shaped objects requires a skilled robotic system. The manipulation of objects that have sensitive top surfaces and a fixed set of neighbors is particularly challenging. To avoid damaging the…

Camouflaged objects are typically assimilated into their backgrounds and exhibit fuzzy boundaries. The complex environmental conditions and the high intrinsic similarity between camouflaged targets and their surroundings pose significant…

Retargeting human kinematic reference motion onto a robot's morphology remains a formidable challenge. Existing methods often produce physical inconsistencies, such as foot sliding, self-collisions, or dynamically infeasible motions, which…

In this work, we explore how a strategic selection of camera movements can facilitate the task of 6D multi-object pose estimation in cluttered scenarios while respecting real-world constraints important in robotics and augmented reality…

We propose a reinforcement-learning algorithm to tackle the challenge of reconstructing phylogenetic trees. The search for the tree that best describes the data is algorithmically challenging, thus all current algorithms for phylogeny…

State-of-the-art object detection systems rely on an accurate set of region proposals. Several recent methods use a neural network architecture to hypothesize promising object locations. While these approaches are computationally efficient,…

We study how to leverage Web images to augment human-curated object detection datasets. Our approach is two-pronged. On the one hand, we retrieve Web images by image-to-image search, which incurs less domain shift from the curated data than…

In this paper we introduce a fully end-to-end approach for visual tracking in videos that learns to predict the bounding box locations of a target object at every frame. An important insight is that the tracking problem can be considered as…

Deep Reinforcement Learning is a promising tool for robotic control, yet practical application is often hindered by the difficulty of designing effective reward functions. Real-world tasks typically require optimizing multiple objectives…

We propose a novel object localization methodology with the purpose of boosting the localization accuracy of state-of-the-art object detection systems. Our model, given a search region, aims at returning the bounding box of an object of…

There are mainly two types of state-of-the-art object detectors. On one hand, we have two-stage detectors, such as Faster R-CNN (Region-based Convolutional Neural Networks) or Mask R-CNN, that (i) use a Region Proposal Network to generate…

Recent advances in vision-based navigation and exploration have shown impressive capabilities in photorealistic indoor environments. However, these methods still struggle with long-horizon tasks and require large amounts of data to…

In the last few years, there has been a growing interest in taking advantage of the 360 panoramic images potential, while managing the new challenges they imply. While several tasks have been improved thanks to the contextual information…

Despite recent advances, object detection in aerial images is still a challenging task. Specific problems in aerial images makes the detection problem harder, such as small objects, densely packed objects, objects in different sizes and…

In order to speed-up classification models when facing a large number of categories, one usual approach consists in organizing the categories in a particular structure, this structure being then used as a way to speed-up the prediction…

Camouflaged object detection intends to discover the concealed objects hidden in the surroundings. Existing methods follow the bio-inspired framework, which first locates the object and second refines the boundary. We argue that the…

We propose a unified object-aware temporal learning framework for multi-view 3D detection and tracking tasks. Having observed that the efficacy of the temporal fusion strategy in recent multi-view perception methods may be weakened by…

We explore the black-box adversarial attack on video recognition models. Attacks are only performed on selected key regions and key frames to reduce the high computation cost of searching adversarial perturbations on a video due to its high…

Learning a policy capable of moving an agent between any two states in the environment is important for many robotics problems involving navigation and manipulation. Due to the sparsity of rewards in such tasks, applying reinforcement…