Related papers: Visual Summary of Value-level Feature Attribution …

While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene. Instance…

Billions of photos are uploaded to the web daily through various types of social networks. Some of these images receive millions of views and become popular, whereas others remain completely unnoticed. This raises the problem of predicting…

Recently, several methods have been proposed to explain the predictions of recurrent neural networks (RNNs), in particular of LSTMs. The goal of these methods is to understand the network's decisions by assigning to each input variable,…

Models for sequential data such as the recurrent neural network (RNN) often implicitly model a sequence as having a fixed time interval between observations and do not account for group-level effects when multiple sequences are observed. We…

Diffusion models have demonstrated remarkable performance in generation tasks. Nevertheless, explaining the diffusion process remains challenging due to it being a sequence of denoising noisy images that are difficult for experts to…

Sparsity of user-to-item rating data becomes one of challenging issues in the recommender systems, which severely deteriorates the recommendation performance. Fortunately, context-aware recommender systems can alleviate the sparsity problem…

P300-based spellers are one of the main methods for EEG-based brain-computer interface, and the detection of the P300 target event with high accuracy is an important prerequisite. The rapid serial visual presentation (RSVP) protocol is of…

Viewpoint estimation from 2D rendered images is helpful in understanding how users select viewpoints for volume visualization and guiding users to select better viewpoints based on previous visualizations. In this paper, we propose a…

Extracting interpretable equations from observational datasets to describe complex natural phenomena is one of the core goals of artificial intelligence. This field is known as symbolic regression (SR). In recent years, Transformer-based…

Deep learning methods are widely applied in digital pathology to address clinical challenges such as prognosis and diagnosis. As one of the most recent applications, deep models have also been used to extract molecular features from whole…

Machine learning systems are being used to automate many types of laborious labeling tasks. Facial actioncoding is an example of such a labeling task that requires copious amounts of time and a beyond average level of human domain…

Videos are inherently multimodal. This paper studies the problem of how to fully exploit the abundant multimodal clues for improved video categorization. We introduce a hybrid deep learning framework that integrates useful clues from…

This paper presents the recurrent estimation of distributions (RED) for modeling real-valued data in a semiparametric fashion. RED models make two novel uses of recurrent neural networks (RNNs) for density estimation of general real-valued…

Visual attention, which assigns weights to image regions according to their relevance to a question, is considered as an indispensable part by most Visual Question Answering models. Although the questions may involve complex relations among…

Deep learning is increasingly used in decision-making tasks. However, understanding how neural networks produce final predictions remains a fundamental challenge. Existing work on interpreting neural network predictions for images often…

Computational models of vision have traditionally been developed in a bottom-up fashion, by hierarchically composing a series of straightforward operations - i.e. convolution and pooling - with the aim of emulating simple and complex cells…

Video quality assessment (VQA) is vital for computer vision tasks, but existing approaches face major limitations: full-reference (FR) metrics require clean reference videos, and most no-reference (NR) models depend on training on costly…

We introduce a class of convolutional neural networks (CNNs) that utilize recurrent neural networks (RNNs) as convolution filters. A convolution filter is typically implemented as a linear affine transformation followed by a non-linear…

Using vision-language models (VLMs) as reward models in reinforcement learning holds promise for reducing costs and improving safety. So far, VLM reward models have only been used for goal-oriented tasks, where the agent must reach a…

Person re-identification (re-ID) aims to retrieve the same person across different cameras. In practice, it still remains a challenging task due to background clutter, variations on body poses and view conditions, inaccurate bounding box…