Related papers: Discovering Attribute Shades of Meaning with the C…

Open-vocabulary semantic segmentation is a challenging task that requires segmenting novel object categories at inference time. Recent studies have explored vision-language pre-training to handle this task, but suffer from unrealistic…

Artwork recommendation is challenging because it requires understanding how users interact with highly subjective content, the complexity of the concepts embedded within the artwork, and the emotional and cognitive reflections they may…

Prompt learning has proven effective in adapting vision language models for downstream tasks. However, existing methods usually append learnable prompt tokens solely with the category names to obtain textual features, which fails to fully…

Crowd counting is an important task in computer vision, which has many applications in video surveillance. Although the regression-based framework has achieved great improvements for crowd counting, how to improve the discriminative power…

Lexical ambiguity presents a profound and enduring challenge to the language sciences. Researchers for decades have grappled with the problem of how language users learn, represent and process words with more than one meaning. Our work…

Deep learning models have achieved remarkable success in different areas of machine learning over the past decade; however, the size and complexity of these models make them difficult to understand. In an effort to make them more…

This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation. The semantic attribute modulation includes various document attributes, such as titles, authors, and document categories. We consider two…

Pedestrian detection is an initial step to perform outdoor scene analysis, which plays an essential role in many real-world applications. Although having enjoyed the merits of deep learning frameworks from the generic object detectors,…

Impressive progress has been made in the fields of computer vision and natural language processing. However, it remains a challenge to find the best point of interaction for these very different modalities. In this chapter we discuss how…

A popular approach to semantic image understanding is to manually tag images with keywords and then learn a mapping from vi- sual features to keywords. Manually tagging images is a subjective pro- cess and the same or very similar visual…

Unsupervised disentanglement has been shown to be theoretically impossible without inductive biases on the models and the data. As an alternative approach, recent methods rely on limited supervision to disentangle the factors of variation…

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

The problem of estimating subjective visual properties from image and video has attracted increasing interest. A subjective visual property is useful either on its own (e.g. image and video interestingness) or as an intermediate…

Scene classification has established itself as a challenging research problem. Compared to images of individual objects, scene images could be much more semantically complex and abstract. Their difference mainly lies in the level of…

In crowd behavior understanding, a model of crowd behavior need to be trained using the information extracted from video sequences. Since there is no ground-truth available in crowd datasets except the crowd behavior labels, most of the…

Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded…

How do computers and intelligent agents view the world around them? Feature extraction and representation constitutes one the basic building blocks towards answering this question. Traditionally, this has been done with carefully engineered…

Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., word embeddings,…

This paper investigates a general framework to discover categories of unlabeled scene images according to their appearances (i.e., textures and structures). We jointly solve the two coupled tasks in an unsupervised manner: (i) classifying…

We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves…