Related papers: Unsupervised Ego- and Exo-centric Dense Procedural…
Action recognition is currently one of the top-challenging research fields in computer vision. Convolutional Neural Networks (CNNs) have significantly boosted its performance but rely on fixed-size spatio-temporal windows of analysis,…
Emotion Recognition in Conversation (ERC) has attracted widespread attention in the natural language processing field due to its enormous potential for practical applications. Existing ERC methods face challenges in achieving generalization…
Current facial emotion recognition systems are predominately trained to predict a fixed set of predefined categories or abstract dimensional values. This constrained form of supervision hinders generalization and applicability, as it…
While exploring visual scenes, humans' scanpaths are driven by their underlying attention processes. Understanding visual scanpaths is essential for various applications. Traditional scanpath models predict the where and when of gaze shifts…
We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…
Human language processing relies on the brain's capacity for predictive inference. We present a machine learning framework for decoding neural (EEG) responses to dynamic visual language stimuli in Deaf signers. Using coherence between…
In this paper, we study the problem of producing a comprehensive video summary following an unsupervised approach that relies on adversarial learning. We build on a popular method where a Generative Adversarial Network (GAN) is trained to…
Understanding affect is central to anticipating human behavior, yet current egocentric vision benchmarks largely ignore the person's emotional states that shape their decisions and actions. Existing tasks in egocentric perception focus on…
Significant inter-individual variability limits the generalization of EEG-based emotion recognition under cross-domain settings. We address two core challenges in multi-source adaptation: (1) dynamically modeling distributional…
Speech encodes a wealth of information related to human behavior and has been used in a variety of automated behavior recognition tasks. However, extracting behavioral information from speech remains challenging including due to inadequate…
Despite the remarkable performance of text-to-image diffusion models in image generation tasks, recent studies have raised the issue that generated images sometimes cannot capture the intended semantic contents of the text prompts, which…
Learning in a multi-target environment without prior knowledge about the targets requires a large amount of samples and makes generalization difficult. To solve this problem, it is important to be able to discriminate targets through…
Emotion perception and adaptive expression are fundamental capabilities in human-agent interaction. While recent advances in speech emotion captioning (SEC) have improved fine-grained emotional modeling, existing systems remain limited to…
Generating videos in the first-person perspective has broad application prospects in the field of augmented reality and embodied intelligence. In this work, we explore the cross-view video prediction task, where given an exo-centric video,…
In this paper, we explore a novel Text-supervised Egocentic Semantic Segmentation (TESS) task that aims to assign pixel-level categories to egocentric images weakly supervised by texts from image-level labels. In this task with prospective…
Human gaze offers rich supervisory signals for understanding visual attention in complex visual environments. In this paper, we propose Eyes on Target, a novel depth-aware and gaze-guided object detection framework designed for egocentric…
Emotion Recognition in Conversations (ERC) aims to predict the emotional state of speakers in conversations, which is essentially a text classification task. Unlike the sentence-level text classification problem, the available supervised…
Learning an agent model that behaves like humans-capable of jointly perceiving the environment, predicting the future, and taking actions from a first-person perspective-is a fundamental challenge in computer vision. Existing methods…
In this paper, we present an unsupervised learning approach for analyzing facial behavior based on a deep generative model combined with a convolutional neural network (CNN). We jointly train a variational auto-encoder (VAE) and a…
Training robust world models requires large-scale, precisely labeled multimodal datasets, a process historically bottlenecked by slow and expensive manual annotation. We present a production-tested GAZE pipeline that automates the…