Related papers: Dynamic Concept Composition for Zero-Example Event…

Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous "events" instead of intensity frames. They offer significant advantages with respect to conventional cameras: high dynamic range (HDR),…

Scaling up visual category recognition to large numbers of classes remains challenging. A promising research direction is zero-shot learning, which does not require any training data to recognize new classes, but rather relies on some form…

Can we teach a robot to recognize and make predictions for activities that it has never seen before? We tackle this problem by learning models for video from text. This paper presents a hierarchical model that generalizes instructional…

Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) proposes one solution to this problem. ZSL trains a model…

In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) in the training set. This is challenging because the same…

Activity recognition is a challenging problem with many practical applications. In addition to the visual features, recent approaches have benefited from the use of context, e.g., inter-relationships among the activities and objects.…

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…

The task of event extraction has long been investigated in a supervised learning paradigm, which is bound by the number and the quality of the training instances. Existing training data must be manually generated through a combination of…

Zero-shot learning (ZSL) aims to recognize unseen classes by aligning images with intermediate class semantics, like human-annotated concepts or class definitions. An emerging alternative leverages Large-scale Language Models (LLMs) to…

We propose a visual analytics system to help a user analyze and steer zero-shot learning models. Zero-shot learning has emerged as a viable scenario for categorizing data that consists of no labeled examples, and thus a promising approach…

We introduce and tackle the problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training. We work with a challenging set of object classes, not restricting ourselves to similar…

We propose a new approach, Synthetic Optimized Layout with Instance Detection (SOLID), to pretrain object detectors with synthetic images. Our "SOLID" approach consists of two main components: (1) generating synthetic images using a…

Many methods have been proposed to detect concept drift, i.e., the change in the distribution of streaming data, due to concept drift causes a decrease in the prediction accuracy of algorithms. However, the most of current detection methods…

Young children demonstrate early abilities to understand their physical world, estimating depth, motion, object coherence, interactions, and many other aspects of physical scene understanding. Children are both data-efficient and flexible…

In this paper we present a simple yet effective approach to extend without supervision any object proposal from static images to videos. Unlike previous methods, these spatio-temporal proposals, to which we refer as tracks, are generated…

In this paper the problem of complex event detection in the continuous domain (i.e. events with unknown starting and ending locations) is addressed. Existing event detection methods are limited to features that are extracted from the local…

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This work provides a new…

Video understanding has long suffered from reliance on large labeled datasets, motivating research into zero-shot learning. Recent progress in language modeling presents opportunities to advance zero-shot video analysis, but constructing an…

Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a model for a single task with supervision. We propose OpenScene, an alternative approach where a model predicts dense features for 3D scene points that are…

Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one…