相关论文: Learning to Visually Connect Actions and their Eff…

Predicting other people's action is key to successful social interactions, enabling us to adjust our own behavior to the consequence of the others' future actions. Studies on action recognition have focused on the importance of individual…

Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning, restricting their ability to incorporate essential dynamic information as the reasoning process evolves. Existing methods that augment…

As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each…

People interact with the real-world largely dependent on visual signal, which are ubiquitous and illustrate detailed demonstrations. In this paper, we explore utilizing visual signals as a new interface for models to interact with the…

Humans observe various actions being performed by other humans (physically or in videos/images) and can draw a wide range of inferences about it beyond what they can visually perceive. Such inferences include determining the aspects of the…

We present Vision in Action (ViA), an active perception system for bimanual robot manipulation. ViA learns task-relevant active perceptual strategies (e.g., searching, tracking, and focusing) directly from human demonstrations. On the…

Visual action planning particularly excels in applications where the state of the system cannot be computed explicitly, such as manipulation of deformable objects, as it enables planning directly from raw images. Even though the field has…

We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person whose actions we…

Foundation models have ushered in a new era for multimodal video understanding by enabling the extraction of rich spatiotemporal and semantic representations. In this work, we introduce a novel graph-based framework that integrates a…

Knowledge tracing (KT) refers to the problem of predicting future learner performance given their past performance in educational applications. Recent developments in KT using flexible deep neural network-based models excel at this task.…

We present a dual-pathway approach for recognizing fine-grained interactions from videos. We build on the success of prior dual-stream approaches, but make a distinction between the static and dynamic representations of objects and their…

In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain. UNITE first…

Estimating the Conditional Average Treatment Effect (CATE) is often constrained by the high cost of obtaining outcome measurements, making active learning essential. However, conventional active learning strategies suffer from a fundamental…

Event cameras have recently been shown beneficial for practical vision tasks, such as action recognition, thanks to their high temporal resolution, power efficiency, and reduced privacy concerns. However, current research is hindered by 1)…

This paper presents a new method to describe spatio-temporal relations between objects and hands, to recognize both interactions and activities within video demonstrations of manual tasks. The approach exploits Scene Graphs to extract key…

One of the central goals of causal machine learning is the accurate estimation of heterogeneous treatment effects from observational data. In recent years, meta-learning has emerged as a flexible, model-agnostic paradigm for estimating…

Chart understanding presents a critical test to the reasoning capabilities of Vision-Language Models (VLMs). Prior approaches face critical limitations: some rely on external tools, making them brittle and constrained by a predefined…

Event perception tasks such as recognizing and localizing actions in streaming videos are essential for scaling to real-world application contexts. We tackle the problem of learning actor-centered representations through the notion of…

Inductive link prediction -- where entities during training and inference stages can be different -- has been shown to be promising for completing continuously evolving knowledge graphs. Existing models of inductive reasoning mainly focus…

Vision-language models (VLMs) exhibit remarkable zero-shot generalization but suffer performance degradation under distribution shifts in downstream tasks, particularly in the absence of labeled data. Test-Time Adaptation (TTA) addresses…