相关论文: Visual Relationship Detection Based on Guided Prop…

Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to…

Some biological mechanisms of early vision are comparatively well understood, but they have yet to be evaluated for their ability to accurately predict and explain human judgments of image similarity. From well-studied simple connectivity…

Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world. For example, it can be used to simulate the environment, or to infer the state of parts of the world that are currently…

In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly…

Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a…

Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of such knowledge transfer drops significantly when distilling…

Lexical Semantics is concerned with how words encode mental representations of the world, i.e., concepts . We call this type of concepts, classification concepts . In this paper, we focus on Visual Semantics , namely on how humans build…

Multimodal image matching seeks pixel-level correspondences between images of different modalities, crucial for cross-modal perception, fusion and analysis. However, the significant appearance differences between modalities make this task…

Driven by a large number of potential applications in areas like bioinformatics, information retrieval and social network analysis, the problem setting of inferring relations between pairs of data objects has recently been investigated…

Scene text instances found in natural images carry explicit semantic information that can provide important cues to solve a wide array of computer vision problems. In this paper, we focus on leveraging multi-modal content in the form of…

Deep learning techniques have been demonstrated to surpass preceding cutting-edge machine learning techniques in recent years, with computer vision being one of the most prominent examples. However, deep learning models suffer from…

Spatial relations between objects in an image have proved useful for structural object recognition. Structural constraints can act as regularization in neural network training, improving generalization capability with small datasets.…

Knowledge distillation is a potential solution for model compression. The idea is to make a small student network imitate the target of a large teacher network, then the student network can be competitive to the teacher one. Most previous…

Sequential recommendation models user interests based on historical behaviors to provide personalized recommendation. Previous sequential recommendation algorithms primarily employ neural networks to extract features of user interests,…

The recent developments in deep learning led to the integration of natural language processing (NLP) with computer vision, resulting in powerful integrated Vision and Language Models (VLMs). Despite their remarkable capabilities, these…

Attributes of words and relations between two words are central to numerous tasks in Artificial Intelligence such as knowledge representation, similarity measurement, and analogy detection. Often when two words share one or more attributes…

Correspondence estimation is one of the most widely researched and yet only partially solved area of computer vision with many applications in tracking, mapping, recognition of objects and environment. In this paper, we propose a novel way…

What is the right supervisory signal to train visual representations? Current approaches in computer vision use category labels from datasets such as ImageNet to train ConvNets. However, in case of biological agents, visual representation…

Transfer learning has become the de facto standard in computer vision and natural language processing, especially where labeled data is scarce. Accuracy can be significantly improved by using pre-trained models and subsequent fine-tuning.…

Reasoning about spatial relationships between objects is essential for many real-world robotic tasks, such as fetch-and-delivery, object rearrangement, and object search. The ability to detect and disambiguate different objects and identify…