Related papers: Adaptive Prototype Model for Attribute-based Multi…

This paper addresses the challenge of point-supervised temporal action detection, in which only one frame per action instance is annotated in the training set. Self-training aims to provide supplementary supervision for the training process…

Mistake detection in procedural tasks is essential for building intelligent systems that support learning and task execution. Existing approaches primarily analyze how an action is performed, while overlooking what it produces, i.e., the…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Action visual tempo characterizes the dynamics and the temporal scale of an action, which is helpful to distinguish human actions that share high similarities in visual dynamics and appearance. Previous methods capture the visual tempo…

In this paper, we study multi-label atomic activity recognition. Despite the notable progress in action recognition, it is still challenging to recognize atomic activities due to a deficiency in a holistic understanding of both multiple…

Domain adaptation is essential for activity recognition to ensure accurate and robust performance across diverse environments, sensor types, and data sources. Unsupervised domain adaptation methods have been extensively studied, yet, they…

This work introduces a new multi-task, parameter-efficient language model (LM) tuning method that learns to transfer knowledge across different tasks via a mixture of soft prompts-small prefix embedding vectors pre-trained for different…

Multi-modal learning, which focuses on utilizing various modalities to improve the performance of a model, is widely used in video recognition. While traditional multi-modal learning offers excellent recognition results, its computational…

With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…

Recently, text-to-motion models have opened new possibilities for creating realistic human motion with greater efficiency and flexibility. However, aligning motion generation with event-level textual descriptions presents unique challenges…

Meta-learning has emerged as a prominent technology for few-shot text classification and has achieved promising performance. However, existing methods often encounter difficulties in drawing accurate class prototypes from support set…

Some of the most severe bottlenecks preventing widespread development of machine learning models for human behavior include a dearth of labeled training data and difficulty of acquiring high quality labels. Active learning is a paradigm for…

Few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. In this work, we propose a novel approach that first summarizes each video into compound prototypes consisting of a…

Attribute representations became relevant in image recognition and word spotting, providing support under the presence of unbalance and disjoint datasets. However, for human activity recognition using sequential data from on-body sensors,…

Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic…

Speech-based machine learning (ML) has been heralded as a promising solution for tracking prosodic and spectrotemporal patterns in real-life that are indicative of emotional changes, providing a valuable window into one's cognitive and…

Few-shot action recognition (FSAR) aims to classify human actions in videos with only a small number of labeled samples per category. The scarcity of training data has driven recent efforts to incorporate additional modalities, particularly…

When reading a story, humans can quickly understand new fictional characters with a few observations, mainly by drawing analogies to fictional and real people they already know. This reflects the few-shot and meta-learning essence of…

Vision-Language Models (VLMs) have demonstrated impressive capabilities in zero-shot action recognition by learning to associate video embeddings with class embeddings. However, a significant challenge arises when relying solely on action…

We consider the problem of few-shot scene adaptive crowd counting. Given a target camera scene, our goal is to adapt a model to this specific scene with only a few labeled images of that scene. The solution to this problem has potential…