相关论文: Hierarchical Video Understanding

With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…

Video-text retrieval is an important yet challenging task in vision-language understanding, which aims to learn a joint embedding space where related video and text instances are close to each other. Most current works simply measure the…

Recently, integrating visual foundation models into large language models (LLMs) to form video understanding systems has attracted widespread attention. Most of the existing models compress diverse semantic information within the whole…

This PhD. Thesis concerns the study and development of hierarchical representations for spatio-temporal visual attention modeling and understanding in video sequences. More specifically, we propose two computational models for visual…

We present a novel algorithm for estimating the broad 3D geometric structure of outdoor video scenes. Leveraging spatio-temporal video segmentation, we decompose a dynamic scene captured by a video into geometric classes, based on…

Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentation, and sentiment analysis. However, effective usage of such…

Natural videos provide rich visual contents for self-supervised learning. Yet most existing approaches for learning spatio-temporal representations rely on manually trimmed videos, leading to limited diversity in visual patterns and limited…

Many human activities take minutes to unfold. To represent them, related works opt for statistical pooling, which neglects the temporal structure. Others opt for convolutional methods, as CNN and Non-Local. While successful in learning…

The standard way of training video models entails sampling at each iteration a single clip from a video and optimizing the clip prediction with respect to the video-level label. We argue that a single clip may not have enough temporal…

Procedures are inherently hierarchical. To "make videos", one may need to "purchase a camera", which in turn may require one to "set a budget". While such hierarchical knowledge is critical for reasoning about complex procedures, most…

In this paper, we develop a neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner. We represent cross-document…

Despite the success of deep learning in video understanding tasks, processing every frame in a video is computationally expensive and often unnecessary in real-time applications. Frame selection aims to extract the most informative and…

Video-language embeddings are a promising avenue for injecting semantics into visual representations, but existing methods capture only short-term associations between seconds-long video clips and their accompanying text. We propose HierVL,…

Most of the current action recognition algorithms are based on deep networks which stack multiple convolutional, pooling and fully connected layers. While convolutional and fully connected operations have been widely studied in the…

Large vision and language models learned directly through image-text associations often lack detailed visual substantiation, whereas image segmentation tasks are treated separately from recognition, supervisedly learned without…

We introduce a framework for learning from unlabeled video what is predictable in the future. Instead of committing up front to features to predict, our approach learns from data which features are predictable. Based on the observation that…

While Multimodal Large Language Models (MLLMs) exhibit strong performance on standard video tasks, their ability to faithfully summarize and reason over complex narratives remains poorly evaluated. Existing summarization benchmarks fragment…

Reinforcement learning practitioners often avoid hierarchical policies, especially in image-based observation spaces. Typically, the single-task performance improvement over flat-policy counterparts does not justify the additional…

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally…

This paper describes a hierarchical learning strategy for generating sparse representations of multivariate datasets. The hierarchy arises from approximation spaces considered at successively finer scales. A detailed analysis of stability,…