相关论文: Winning the CVPR'2021 Kinetics-GEBD Challenge: Con…
Joint video-language learning has received increasing attention in recent years. However, existing works mainly focus on single or multiple trimmed video clips (events), which makes human-annotated event boundaries necessary during…
Video segmentation consists of a frame-by-frame selection process of meaningful areas related to foreground moving objects. Some applications include traffic monitoring, human tracking, action recognition, efficient video surveillance, and…
The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of…
We propose a new application of embedding techniques for problem retrieval in adaptive tutoring. The objective is to retrieve problems whose mathematical concepts are similar. There are two challenges: First, like sentences, problems…
Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack…
Prediction is a central task of machine learning. Our goal is to solve large scale prediction problems using Generative Quantile Bayesian Prediction (GQBP).By directly learning predictive quantiles rather than densities we achieve a number…
The visual cues from multiple support regions of different sizes and resolutions are complementary in classifying a candidate box in object detection. Effective integration of local and contextual visual cues from these regions has become a…
Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification. However, unlike humans, CNNs leverage spurious features, such as background information to make decisions.…
Most anomaly detection (AD) models are learned using only normal samples in an unsupervised way, which may result in ambiguous decision boundary and insufficient discriminability. In fact, a few anomaly samples are often available in…
Depth estimation models have shown promising performance on clear scenes but fail to generalize to adverse weather conditions due to illumination variations, weather particles, etc. In this paper, we propose WeatherDepth, a self-supervised…
We consider the problem of learning deep generative models from data. We formulate a method that generates an independent sample via a single feedforward pass through a multilayer perceptron, as in the recently proposed generative…
Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same…
Multimedia event detection is the task of detecting a specific event of interest in an user-generated video on websites. The most fundamental challenge facing this task lies in the enormously varying quality of the video as well as the…
Sequential recommender systems identify user preferences from their past interactions to predict subsequent items optimally. Although traditional deep-learning-based models and modern transformer-based models in previous studies capture…
This paper describes the system proposed for the SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection. We focused our approach on the detection problem. Given the semantics of words captured by temporal word embeddings in…
Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…
In this paper, we introduce a contrastive learning framework for keypoint detection (CoKe). Keypoint detection differs from other visual tasks where contrastive learning has been applied because the input is a set of images in which…
Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moments of varying lengths, recent methods employ a multi-level…
Recently, deep metric learning techniques received attention, as the learned distance representations are useful to capture the similarity relationship among samples and further improve the performance of various of supervised or…
In the context of robotic grasping, object segmentation encounters several difficulties when faced with dynamic conditions such as real-time operation, occlusion, low lighting, motion blur, and object size variability. In response to these…