Related papers: Non-parametric Contextual Relationship Learning fo…
We present a filtering-based method for semantic mapping to simultaneously detect objects and localize their 6 degree-of-freedom pose. For our method, called Contextual Temporal Mapping (or CT-Map), we represent the semantic map as a belief…
The small objects in images and videos are usually not independent individuals. Instead, they more or less present some semantic and spatial layout relationships with each other. Modeling and inferring such intrinsic relationships can…
How do humans recognize the action "opening a book" ? We argue that there are two important cues: modeling temporal shape dynamics and modeling functional relationships between humans and objects. In this paper, we propose to represent…
This paper introduces a novel approach to Generalized Category Discovery (GCD) by leveraging the concept of contextuality to enhance the identification and classification of categories in unlabeled datasets. Drawing inspiration from human…
Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based…
Are we using the right potential functions in the Conditional Random Field models that are popular in the Vision community? Semantic segmentation and other pixel-level labelling tasks have made significant progress recently due to the deep…
Increasing the semantic understanding and contextual awareness of machine learning models is important for improving robustness and reducing susceptibility to data shifts. In this work, we leverage contextual awareness for the anomaly…
Causal structure learning with data from multiple contexts carries both opportunities and challenges. Opportunities arise from considering shared and context-specific causal graphs enabling to generalize and transfer causal knowledge across…
Visual relationship detection can bridge the gap between computer vision and natural language for scene understanding of images. Different from pure object recognition tasks, the relation triplets of subject-predicate-object lie on an…
Automatic video captioning is challenging due to the complex interactions in dynamic real scenes. A comprehensive system would ultimately localize and track the objects, actions and interactions present in a video and generate a description…
We present a novel Cross-Class Relevance Learning approach for the task of temporal concept localization. Most localization architectures rely on feature extraction layers followed by a classification layer which outputs class probabilities…
Semantic video segmentation is challenging due to the sheer amount of data that needs to be processed and labeled in order to construct accurate models. In this paper we present a deep, end-to-end trainable methodology to video segmentation…
Temporal action localization is an important and challenging task that aims to locate temporal regions in real-world untrimmed videos where actions occur and recognize their classes. It is widely acknowledged that video context is a…
We propose a novel framework for video understanding, called Temporally Contextualized CLIP (TC-CLIP), which leverages essential temporal information through global interactions in a spatio-temporal domain within a video. To be specific, we…
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…
Video captioning targets interpreting the complex visual contents as text descriptions, which requires the model to fully understand video scenes including objects and their interactions. Prevailing methods adopt off-the-shelf object…
Structured scene descriptions of images are useful for the automatic processing and querying of large image databases. We show how the combination of a semantic and a visual statistical model can improve on the task of mapping images to…
People's social relationships are often manifested through their surroundings, with certain objects or interactions acting as symbols for specific relationships, e.g., wedding rings, roses, hugs, or holding hands. This brings unique…
This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low…
As an important and challenging problem in computer vision, video saliency detection is typically cast as a spatiotemporal context modeling problem over consecutive frames. As a result, a key issue in video saliency detection is how to…