Related papers: Jointly Discovering Visual Objects and Spoken Word…
In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we…
It is not always possible to recognise objects and infer material properties for a scene from visual cues alone, since objects can look visually similar whilst being made of very different materials. In this paper, we therefore present an…
The ability to describe images with natural language sentences is the hallmark for image and language understanding. Such a system has wide ranging applications such as annotating images and using natural sentences to search for images.In…
Audio-visual pre-trained models have gained substantial attention recently and demonstrated superior performance on various audio-visual tasks. This study investigates whether pre-trained audio-visual models demonstrate non-arbitrary…
Image captioning attempts to generate a sentence composed of several linguistic words, which are used to describe objects, attributes, and interactions in an image, denoted as visual semantic units in this paper. Based on this view, we…
When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the…
Supervised learning methods can solve the given problem in the presence of a large set of labeled data. However, the acquisition of a dataset covering all the target classes typically requires manual labeling which is expensive and…
The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples…
Models of acoustic word embeddings (AWEs) learn to map variable-length spoken word segments onto fixed-dimensionality vector representations such that different acoustic exemplars of the same word are projected nearby in the embedding…
Our brains combine vision and hearing to create a more elaborate interpretation of the world. When the visual input is insufficient, a rich panoply of sounds can be used to describe our surroundings. Since more than 1,000 hours of videos…
We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framework to synthesize masked binaural (multi-channel) audio…
Pretraining general-purpose visual features has become a crucial part of tackling many computer vision tasks. While one can learn such features on the extensively-annotated ImageNet dataset, recent approaches have looked at ways to allow…
Most current captioning systems use language models trained on data from specific settings, such as image-based captioning via Amazon Mechanical Turk, limiting their ability to generalize to other modality distributions and contexts. This…
Speech is understood better by using visual context; for this reason, there have been many attempts to use images to adapt automatic speech recognition (ASR) systems. Current work, however, has shown that visually adapted ASR models only…
Personal robots and driverless cars need to be able to operate in novel environments and thus quickly and efficiently learn to recognise new object classes. We address this problem by considering the task of video object segmentation.…
Large-scale pre-trained image-text models exhibit robust multimodal representations, yet applying the Contrastive Language-Image Pre-training (CLIP) model to audio-visual localization remains challenging. Replacing the classification token…
The objective of this work is to localize the sound sources in visual scenes. Existing audio-visual works employ contrastive learning by assigning corresponding audio-visual pairs from the same source as positives while randomly mismatched…
Human infants learn the names of objects and develop their own conceptual systems without explicit supervision. In this study, we propose methods for learning aligned vision-language conceptual systems inspired by infants' word learning…
We propose a learning model for the task of visual storytelling. The main idea is to predict anchor word embeddings from the images and use the embeddings and the image features jointly to generate narrative sentences. We use the embeddings…
This paper proposes an automatic spatially-aware concept discovery approach using weakly labeled image-text data from shopping websites. We first fine-tune GoogleNet by jointly modeling clothing images and their corresponding descriptions…