Related papers: Learning Human Action Recognition Representations …

Automated systems that detect deception in high-stakes situations can enhance societal well-being across medical, social work, and legal domains. Existing models for detecting high-stakes deception in videos have been supervised, but…

Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what…

The performance of differentially private machine learning can be boosted significantly by leveraging the transfer learning capabilities of non-private models pretrained on large public datasets. We critically review this approach. We…

User modeling is critical for many personalized web services. Many existing methods model users based on their behaviors and the labeled data of target tasks. However, these methods cannot exploit useful information in unlabeled user…

Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving. Given the heavy reliance of current trajectory forecasting models on data-driven methodologies, we aim…

This work addresses the problem of anonymizing the identity of faces in a dataset of images, such that the privacy of those depicted is not violated, while at the same time the dataset is useful for downstream task such as for training…

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…

Wearable accelerometers are widely used for continuous monitoring of physical activity. Supervised machine learning and deep learning algorithms have long been used to extract meaningful activity information from raw accelerometry data, but…

The lack of large-scale real datasets with annotations makes transfer learning a necessity for video activity understanding. We aim to develop an effective method for few-shot transfer learning for first-person action classification. We…

Pre-training produces representations that are effective for a wide range of downstream tasks, but it is still unclear what properties of pre-training are necessary for effective gains. Notably, recent work shows that even pre-training on…

We address the computational problem of novel human pose synthesis. Given an image of a person and a desired pose, we produce a depiction of that person in that pose, retaining the appearance of both the person and background. We present a…

Federated learning enables training a global machine learning model from data distributed across multiple sites, without having to move the data. This is particularly relevant in healthcare applications, where data is rife with personal,…

Tiny Actions Challenge focuses on understanding human activities in real-world surveillance. Basically, there are two main difficulties for activity recognition in this scenario. First, human activities are often recorded at a distance, and…

Human motion synthesis is an important problem with applications in graphics, gaming and simulation environments for robotics. Existing methods require accurate motion capture data for training, which is costly to obtain. Instead, we…

Deep video action recognition models have been highly successful in recent years but require large quantities of manually annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic…

The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that…

Generating and representing human behavior are of major importance for various computer vision applications. Commonly, human video synthesis represents behavior as sequences of postures while directly predicting their likely progressions or…

In the context of imitation learning applied to dexterous robotic hands, the high complexity of the systems makes learning complex manipulation tasks challenging. However, the numerous datasets depicting human hands in various different…

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

We address the problem of data augmentation for video action recognition. Standard augmentation strategies in video are hand-designed and sample the space of possible augmented data points either at random, without knowing which augmented…