Related papers: Learning Behavioral Representations of Human Mobil…

One of the ubiquitous representation of long DNA sequence is dividing it into shorter k-mer components. Unfortunately, the straightforward vector encoding of k-mer as a one-hot vector is vulnerable to the curse of dimensionality. Worse yet,…

Recent advances in multimodal learning have largely relied on pairwise contrastive objectives to align different modalities, such as text, video, and audio, in a shared embedding space. While effective in bi-modal setups, these approaches…

Visual Emotion Analysis (VEA) has attracted increasing attention recently with the prevalence of sharing images on social networks. Since human emotions are ambiguous and subjective, it is more reasonable to address VEA in a label…

Players in the online ad ecosystem are struggling to acquire the user data required for precise targeting. Audience look-alike modeling has the potential to alleviate this issue, but models' performance strongly depends on quantity and…

Recent years brought advancements in using neural networks for representation learning of various language or visual phenomena. New methods freed data scientists from hand-crafting features for common tasks. Similarly, problems that require…

In this work, we present MoConVQ, a novel unified framework for physics-based motion control leveraging scalable discrete representations. Building upon vector quantized variational autoencoders (VQ-VAE) and model-based reinforcement…

We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses. In this context, a popular approach consists of using a Conditional Variational…

Trajectory prediction is an essential task for successful human robot interaction, such as in autonomous driving. In this work, we address the problem of predicting future pedestrian trajectories in a first person view setting with a moving…

Well structured visual representations can make robot learning faster and can improve generalization. In this paper, we study how we can acquire effective object-centric representations for robotic manipulation tasks without human labeling…

Reinforcement learning (RL) agents make decisions using nothing but observations from the environment, and consequently, heavily rely on the representations of those observations. Though some recent breakthroughs have used vector-based…

Automatically reasoning about future human behaviors is a difficult problem but has significant practical applications to assistive systems. Part of this difficulty stems from learning systems' inability to represent all kinds of behaviors.…

Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME…

In recent years, cross-modal retrieval has drawn much attention due to the rapid growth of multimodal data. It takes one type of data as the query to retrieve relevant data of another type. For example, a user can use a text to retrieve…

Similar to humans, robots benefit from interacting with their environment through a number of different sensor modalities, such as vision, touch, sound. However, learning from different sensor modalities is difficult, because the learning…

Photorealistic rendering of dynamic humans is an important ability for telepresence systems, virtual shopping, synthetic data generation, and more. Recently, neural rendering methods, which combine techniques from computer graphics and…

Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a learned model of the environment for motion prediction. This modularity…

Many learning tasks involve multi-modal data streams, where continuous data from different modes convey a comprehensive description about objects. A major challenge in this context is how to efficiently interpret multi-modal information in…

Self-supervised pre-training paradigms have been extensively explored in the field of skeleton-based action recognition. In particular, methods based on masked prediction have pushed the performance of pre-training to a new height. However,…

The theme of human mobility is transversal to multiple fields of study and applications, from ad-hoc networks to smart cities, from transportation planning to recommendation systems on social networks. Despite the considerable efforts made…

In this paper, we propose a novel trajectory learning method that exploits motion trajectories on topological map using recurrent neural network for temporally consistent geolocalization of object. Inspired by human's ability to both be…