Related papers: Robust Region Feature Synthesizer for Zero-Shot Ob…

Zero-shot object navigation (ZSON) in large-scale outdoor environments faces many challenges; we specifically address a coupled one: long-range targets that reduce to tiny projections and intermittent visibility due to partial or complete…

Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen classes to unseen ones. Semantic knowledge is learned from attribute descriptions shared between different classes, which act as strong…

In image recognition, there are many cases where training samples cannot cover all target classes. Zero-shot learning (ZSL) utilizes the class semantic information to classify samples of the unseen categories that have no corresponding…

We propose a novel Generalized Zero-Shot learning (GZSL) method that is agnostic to both unseen images and unseen semantic vectors during training. Prior works in this context propose to map high-dimensional visual features to the semantic…

Tracking and segmenting multiple similar objects with distinct or complex parts in long-term videos is particularly challenging due to the ambiguity in identifying target components and the confusion caused by occlusion, background clutter,…

Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their semantic descriptions. Some recent papers have shown the importance of localized features together with fine-tuning…

Zero-shot learning (ZSL) aims at recognizing classes for which no visual sample is available at training time. To address this issue, one can rely on a semantic description of each class. A typical ZSL model learns a mapping between the…

The robustness of object detection algorithms plays a prominent role in real-world applications, especially in uncontrolled environments due to distortions during image acquisition. It has been proven that the performance of object…

Zero-shot learning, which studies the problem of object classification for categories for which we have no training examples, is gaining increasing attention from community. Most existing ZSL methods exploit deterministic transfer learning…

Salient object detection (SOD), which aims to identify and locate the most salient pixels or regions in images, has been attracting more and more interest due to its various real-world applications. However, this vision task is quite…

Human-object interaction (HOI) detection aims to locate human-object pairs and identify their interaction categories in images. Most existing methods primarily focus on supervised learning, which relies on extensive manual HOI annotations.…

Generalized Zero-Shot Learning (GZSL) and Open-Set Recognition (OSR) are two mainstream settings that greatly extend conventional visual object recognition. However, the limitations of their problem settings are not negligible. The novel…

We present a novel counterfactual framework for both Zero-Shot Learning (ZSL) and Open-Set Recognition (OSR), whose common challenge is generalizing to the unseen-classes by only training on the seen-classes. Our idea stems from the…

Robustness is a fundamental aspect for developing safe and trustworthy models, particularly when they are deployed in the open world. In this work we analyze the inherent capability of one-stage object detectors to robustly operate in the…

We aim for zero-shot localization and classification of human actions in video. Where traditional approaches rely on global attribute or object classification scores for their zero-shot knowledge transfer, our main contribution is a…

Zero-shot detection (ZSD), i.e., detection on classes not seen during training, is essential for real world detection use-cases, but remains a difficult task. Recent research attempts ZSD with detection models that output embeddings instead…

Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to unseen ones so that the latter can be recognised without any training samples. This is made possible by learning a projection function between a feature space and a…

Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions. Since attributes are often related to specific parts of objects, many recent works…

Recently, the availability of remote sensing imagery from aerial vehicles and satellites constantly improved. For an automated interpretation of such data, deep-learning-based object detectors achieve state-of-the-art performance. However,…

Zero-Shot Learning (ZSL), which aims at automatically recognizing unseen objects, is a promising learning paradigm to understand new real-world knowledge for machines continuously. Recently, the Knowledge Graph (KG) has been proven as an…