Related papers: Multi-Task Learning of Object State Changes from U…
Learned visuomotor policies have shown considerable success as an alternative to traditional, hand-crafted frameworks for robotic manipulation. Surprisingly, an extension of these methods to the multiview domain is relatively unexplored. A…
Data-driven approaches to assist operating room (OR) workflow analysis depend on large curated datasets that are time consuming and expensive to collect. On the other hand, we see a recent paradigm shift from supervised learning to…
Consider the following problem: given a few demonstrations of a task across a few different objects, how can a robot learn to perform that same task on new, previously unseen objects? This is challenging because the large variety of objects…
The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem…
Learning how to interact with objects is an important step towards embodied visual intelligence, but existing techniques suffer from heavy supervision or sensing requirements. We propose an approach to learn human-object interaction…
Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled…
We present a new method to learn video representations from unlabeled data. Given large-scale unlabeled video data, the objective is to benefit from such data by learning a generic and transferable representation space that can be directly…
Single-task learning in artificial neural networks will be able to learn the model very well, and the benefits brought by transferring knowledge thus become limited. In this regard, when the number of tasks increases (e.g., semantic…
Anticipating future actions is a highly challenging task due to the diversity and scale of potential future actions; yet, information from different modalities help narrow down plausible action choices. Each modality can provide diverse and…
Humans excel at learning long-horizon tasks from demonstrations augmented with textual commentary, as evidenced by the burgeoning popularity of tutorial videos online. Intuitively, this capability can be separated into 2 distinct subtasks -…
We tackle the problem of learning complex, general behaviors directly in the real world. We propose an approach for robots to efficiently learn manipulation skills using only a handful of real-world interaction trajectories from many…
In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…
Videos capture events that typically contain multiple sequential, and simultaneous, actions even in the span of only a few seconds. However, most large-scale datasets built to train models for action recognition in video only provide a…
Wearable cameras stand out as one of the most promising devices for the upcoming years, and as a consequence, the demand of computer algorithms to automatically understand the videos recorded with them is increasing quickly. An automatic…
Robots are expected to replace menial tasks such as housework. Some of these tasks include nonprehensile manipulation performed without grasping objects. Nonprehensile manipulation is very difficult because it requires considering the…
Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…
Current state-of-the-art methods cast monocular 3D human pose estimation as a learning problem by training neural networks on large data sets of images and corresponding skeleton poses. In contrast, we propose an approach that can exploit…
Learning object segmentation in image and video datasets without human supervision is a challenging problem. Humans easily identify moving salient objects in videos using the gestalt principle of common fate, which suggests that what moves…
In this work, we study the problem of how to leverage instructional videos to facilitate the understanding of human decision-making processes, focusing on training a model with the ability to plan a goal-directed procedure from real-world…
Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis. Nonetheless, most recent methods in the literature handle the two problems separately.…