相关论文: Discovering Human Interactions in Videos with Limi…

The increasing pervasiveness of social media creates new opportunities to study human social behavior, while challenging our capability to analyze their massive data streams. One of the emerging tasks is to distinguish between different…

Segmentation models achieve high accuracy on benchmarks but often fail in real-world domains by relying on spurious correlations instead of true object boundaries. We propose a human-in-the-loop interactive framework that enables…

Large multi-modal models (LMMs) show increasing performance in realistic visual tasks for images and, more recently, for videos. For example, given a video sequence, such models are able to describe in detail objects, the surroundings and…

This paper presents a new large-scale dataset for recognition and temporal localization of human actions collected from Web videos. We refer to it as HACS (Human Action Clips and Segments). We leverage both consensus and disagreement among…

Robust face clustering is a vital step in enabling computational understanding of visual character portrayal in media. Face clustering for long-form content is challenging because of variations in appearance and lack of supporting…

Human-object interaction segmentation is a fundamental task of daily activity understanding, which plays a crucial role in applications such as assistive robotics, healthcare, and autonomous systems. Most existing learning-based methods…

Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider…

Most person re-identification methods, being supervised techniques, suffer from the burden of massive annotation requirement. Unsupervised methods overcome this need for labeled data, but perform poorly compared to the supervised…

The analysis of the ubiquitous human-human interactions is pivotal for understanding humans as social beings. Existing human-human interaction datasets typically suffer from inaccurate body motions, lack of hand gestures and fine-grained…

Many visual recognition problems can be approached by counting instances. To determine whether an event is present in a long internet video, one could count how many frames seem to contain the activity. Classifying the activity of a group…

Human brain is continuously inundated with the multisensory information and their complex interactions coming from the outside world at any given moment. Such information is automatically analyzed by binding or segregating in our brain.…

In this paper, we investigate the use of an unsupervised label clustering technique and demonstrate that it enables substantial improvements in visual relationship prediction accuracy on the Person in Context (PIC) dataset. We propose to…

We study the problem of determining the emergent behaviors that are possible given a functionally heterogeneous swarm of robots with limited capabilities. Prior work has considered behavior search for homogeneous swarms and proposed the use…

A significant proportion of individuals' daily activities is experienced through digital devices. Smartphones in particular have become one of the preferred interfaces for content consumption and social interaction. Identifying the content…

In a world of pervasive cameras, public spaces are often captured from multiple perspectives by cameras of different types, both fixed and mobile. An important problem is to organize these heterogeneous collections of videos by finding…

Recent Multi-modal Large Language Models (MLLMs) have made great progress in video understanding. However, their performance on videos involving human actions is still limited by the lack of high-quality data. To address this, we introduce…

Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative…

Video object segmentation can be considered as one of the most challenging computer vision problems. Indeed, so far, no existing solution is able to effectively deal with the peculiarities of real-world videos, especially in cases of…

Optimized scene representation is an important characteristic of a framework for detecting abnormalities on live videos. One of the challenges for detecting abnormalities in live videos is real-time detection of objects in a non-parametric…

The temporal action segmentation task segments videos temporally and predicts action labels for all frames. Fully supervising such a segmentation model requires dense frame-wise action annotations, which are expensive and tedious to…