相关论文: WhyAct: Identifying Action Reasons in Lifestyle Vl…

We consider the task of identifying human actions visible in online videos. We focus on the widely spread genre of lifestyle vlogs, which consist of videos of people performing actions while verbally describing them. Our goal is to identify…

This paper introduces a new video-and-language dataset with human actions for multimodal logical inference, which focuses on intentional and aspectual expressions that describe dynamic human actions. The dataset consists of 200 videos,…

We consider the task of temporal human action localization in lifestyle vlogs. We introduce a novel dataset consisting of manual annotations of temporal localization for 13,000 narrated actions in 1,200 video clips. We present an extensive…

We address the problem of accurate capture of interactive behaviors between two people in daily scenarios. Most previous works either only consider one person or solely focus on conversational gestures of two people, assuming the body…

We introduce the task of automatic human action co-occurrence identification, i.e., determine whether two human actions can co-occur in the same interval of time. We create and make publicly available the ACE (Action Co-occurrencE) dataset,…

What is the right way to reason about human activities? What directions forward are most promising? In this work, we analyze the current state of human activity understanding in videos. The goal of this paper is to examine datasets,…

We address the problem of accurate capture and expressive modelling of interactive behaviors happening between two persons in daily scenarios. Different from previous works which either only consider one person or focus on conversational…

In online action detection, the goal is to detect the start of an action in a video stream as soon as it happens. For instance, if a child is chasing a ball, an autonomous car should recognize what is going on and respond immediately. This…

Our world is full of varied actions and moves across specialized domains that we, as humans, strive to identify and understand. Within any single domain, actions can often appear quite similar, making it challenging for deep models to…

Vision-Language Models (VLMs) have achieved impressive progress in perceiving and describing visual environments. However, their ability to proactively reason and act based solely on visual inputs, without explicit textual prompts, remains…

Understanding human actions is a key problem in computer vision. However, recognizing actions is only the first step of understanding what a person is doing. In this paper, we introduce the problem of predicting why a person has performed…

Causality helps people reason about and understand complex systems, particularly through what-if analyses that explore how interventions might alter outcomes. Although existing methods embrace causal reasoning using interventions and…

There is growing interest in artificial intelligence to build socially intelligent robots. This requires machines to have the ability to "read" people's emotions, motivations, and other factors that affect behavior. Towards this goal, we…

Captioning is a crucial and challenging task for video understanding. In videos that involve active agents such as humans, the agent's actions can bring about myriad changes in the scene. Observable changes such as movements, manipulations,…

A major stumbling block to progress in understanding basic human interactions, such as getting out of bed or opening a refrigerator, is lack of good training data. Most past efforts have gathered this data explicitly: starting with a…

Human activity recognition is typically addressed by detecting key concepts like global and local motion, features related to object classes present in the scene, as well as features related to the global context. The next open challenges…

Fine-grained understanding of human actions and poses in videos is essential for human-centric AI applications. In this work, we introduce ActionArt, a fine-grained video-caption dataset designed to advance research in human-centric…

We present ExAct, a new video-language benchmark for expert-level understanding of skilled physical human activities. Our new benchmark contains 3521 expert-curated video question-answer pairs spanning 11 physical activities in 6 domains:…

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…

Despite the rapid progress, existing works on action understanding focus strictly on one type of action agent, which we call actor---a human adult, ignoring the diversity of actions performed by other actors. To overcome this narrow…