相关论文: Stochastic Coherence Over Attention Trajectory For…

We introduce a novel self-supervised learning approach to learn representations of videos that are responsive to changes in the motion dynamics. Our representations can be learned from data without human annotation and provide a substantial…

The attribution method provides a direction for interpreting opaque neural networks in a visual way by identifying and visualizing the input regions/pixels that dominate the output of a network. Regarding the attribution method for visually…

Predicting future frames of a video is challenging because it is difficult to learn the uncertainty of the underlying factors influencing their contents. In this paper, we propose a novel video prediction model, which has…

Modern video understanding systems excel at tasks such as scene classification, object detection, and short video retrieval. However, as video analysis becomes increasingly central to real-world applications, there is a growing need for…

When humans perform a task, such as playing a game, they selectively pay attention to certain parts of the visual input, gathering relevant information and sequentially combining it to build a representation from the sensory data. In this…

Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…

This paper proposes a simple self-supervised approach for learning a representation for visual correspondence from raw video. We cast correspondence as prediction of links in a space-time graph constructed from video. In this graph, the…

Neural processes (NPs) aim to stochastically complete unseen data points based on a given context dataset. NPs essentially leverage a given dataset as a context representation to derive a suitable identifier for a novel task. To improve the…

We propose a novel recurrent attentional structure to localize and recognize objects jointly. The network can learn to extract a sequence of local observations with detailed appearance and rough context, instead of sliding windows or…

Self-supervised learning holds the promise of learning good representations from real-world continuous uncurated data streams. However, most existing works in visual self-supervised learning focus on static images or artificial data…

This paper proposes a self-supervised objective for learning representations that localize objects under occlusion - a property known as object permanence. A central question is the choice of learning signal in cases of total occlusion.…

Current automatic vision systems face two major challenges: scalability and extreme variability of appearance. First, the computational time required to process an image typically scales linearly with the number of pixels in the image,…

Continual Learning (CL) and Streaming Machine Learning (SML) study the ability of agents to learn from a stream of non-stationary data. Despite sharing some similarities, they address different and complementary challenges. While SML…

Video analysis tasks rely heavily on identifying the pixels from different frames that correspond to the same visual target. To tackle this problem, recent studies have advocated feature learning methods that aim to learn distinctive…

Robust and efficient learning remains a challenging problem in robotics, in particular with complex visual inputs. Inspired by human attention mechanism, with which we quickly process complex visual scenes and react to changes in the…

Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio, thanks to their temporally uni-directional attention mechanism, which models correlations between the current token and previous…

When an agent acquires new information, ideally it would immediately be capable of using that information to understand its environment. This is not possible using conventional deep neural networks, which suffer from catastrophic forgetting…

Self-supervised methods have shown remarkable progress in learning high-level semantics and low-level temporal correspondence. Building on these results, we take one step further and explore the possibility of integrating these two features…

Wearable cameras are becoming more and more popular in several applications, increasing the interest of the research community in developing approaches for recognizing actions from the first-person point of view. An open challenge in…

Dynamic scene understanding is the ability of a computer system to interpret and make sense of the visual information present in a video of a real-world scene. In this thesis, we present a series of frameworks for dynamic scene…