Related papers: Visual Word Selection without Re-Coding and Re-Poo…
Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding,…
When deriving contextualized word representations from language models, a decision needs to be made on how to obtain one for out-of-vocabulary (OOV) words that are segmented into subwords. What is the best way to represent these words with…
Image cropping has progressed tremendously under the data-driven paradigm. However, current approaches do not account for the intentions of the user, which is an issue especially when the composition of the input image is complex. Moreover,…
Data representation is a fundamental task in machine learning. The representation of data affects the performance of the whole machine learning system. In a long history, the representation of data is done by feature engineering, and…
In this paper, a novel encoding scheme combining Fisher vector and bag-of-words encodings has been proposed for recognizing action in videos. The proposed Hyper-Fisher vector encoding is sum of local Fisher vectors which are computed based…
Data subset selection aims to find a smaller yet informative subset of a large dataset that can approximate the full-dataset training, addressing challenges associated with training neural networks on large-scale datasets. However, existing…
Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve…
Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the…
Image segmentation from referring expressions is a joint vision and language modeling task, where the input is an image and a textual expression describing a particular region in the image; and the goal is to localize and segment the…
As a fundamental task in natural language processing, word embedding converts each word into a representation in a vector space. A challenge with word embedding is that as the vocabulary grows, the vector space's dimension increases, which…
Language modality within the vision language pretraining framework is innately discretized, endowing each word in the language vocabulary a semantic meaning. In contrast, visual modality is inherently continuous and high-dimensional, which…
The bag-of-words (BoW) model treats images as sets of local descriptors and represents them by visual word histograms. The Fisher vector (FV) representation extends BoW, by considering the first and second order statistics of local…
Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for…
In this paper, we discuss the adaptation of our decentralized place recognition method described in [1] to full image descriptors. As we had shown, the key to making a scalable decentralized visual place recognition lies in exploting…
Loop closing is a fundamental part of simultaneous localization and mapping (SLAM) for autonomous mobile systems. In the field of visual SLAM, bag of words (BoW) has achieved great success in loop closure. The BoW features for loop…
Existing open-vocabulary object detection (OVD) develops methods for testing unseen categories by aligning object region embeddings with corresponding VLM features. A recent study leverages the idea that VLMs implicitly learn compositional…
Developments in weakly supervised and self-supervised models could enable speech technology in low-resource settings where full transcriptions are not available. We consider whether keyword localisation is possible using two forms of weak…
The bag-of-words model is a standard representation of text for many linear classifier learners. In many problem domains, linear classifiers are preferred over more complex models due to their efficiency, robustness and interpretability,…
The high demand for computer science education has led to high enrollments, with thousands of students in many introductory courses. In such large courses, it can be overwhelmingly difficult for instructors to understand class-wide…
Recent literature suggests that averaged word vectors followed by simple post-processing outperform many deep learning methods on semantic textual similarity tasks. Furthermore, when averaged word vectors are trained supervised on large…