Related papers: Scene-wise Adaptive Network for Dynamic Cold-start…
Trajectory prediction aims to forecast agents' possible future locations considering their observations along with the video context. It is strongly needed by many autonomous platforms like tracking, detection, robot navigation, and…
Vehicle detection and localization in complex traffic scenarios pose significant challenges due to the interference of moving objects. Traditional methods often rely on outlier exclusions or semantic segmentations, which suffer from low…
Predicting the future motion of surrounding road users is a crucial and challenging task for autonomous driving (AD) and various advanced driver-assistance systems (ADAS). Planning a safe future trajectory heavily depends on understanding…
Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks…
CTR models play a vital role in improving user experience and boosting business revenue in many online personalized services. However, current CTR models generally encounter bottlenecks in performance improvement. Inspired by the scaling…
While deep learning has obtained state-of-the-art results in many applications, the adaptation of neural network architectures to incorporate new output features remains a challenge, as neural networks are commonly trained to produce a…
Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications. State-of-the-art recurrent neural networks (RNN) based models map an input…
Reading text in the wild is a very challenging task due to the diversity of text instances and the complexity of natural scenes. Recently, the community has paid increasing attention to the problem of recognizing text instances with…
Multi-scenario recommendation is dedicated to retrieve relevant items for users in multiple scenarios, which is ubiquitous in industrial recommendation systems. These scenarios enjoy portions of overlaps in users and items, while the…
The ability of accurate depth prediction by a convolutional neural network (CNN) is a major challenge for its wide use in practical visual simultaneous localization and mapping (SLAM) applications, such as enhanced camera tracking and dense…
The problem of Scene flow estimation in depth videos has been attracting attention of researchers of robot vision, due to its potential application in various areas of robotics. The conventional scene flow methods are difficult to use in…
In the Click-Through Rate (CTR) prediction scenario, user's sequential behaviors are well utilized to capture the user interest in the recent literature. However, despite being extensively studied, these sequential methods still suffer from…
The multi-modality and stochastic characteristics of human behavior make motion prediction a highly challenging task, which is critical for autonomous driving. While deep learning approaches have demonstrated their great potential in this…
Recommendation systems are essential for personalizing e-commerce shopping experiences. Among these, Trigger-Induced Recommendation (TIR) has emerged as a key scenario, which utilizes a trigger item (explicitly represents a user's…
Scene text recognition, as a cross-modal task involving vision and text, is an important research topic in computer vision. Most existing methods use language models to extract semantic information for optimizing visual recognition.…
Semantic segmentation methods have achieved outstanding performance thanks to deep learning. Nevertheless, when such algorithms are deployed to new contexts not seen during training, it is necessary to collect and label scene-specific data…
Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes…
In recent years, scene text recognition is always regarded as a sequence-to-sequence problem. Connectionist Temporal Classification (CTC) and Attentional sequence recognition (Attn) are two very prevailing approaches to tackle this problem…
Artificial intelligence systems predominantly rely on static data distributions, making them ineffective in dynamic real-world environments, such as cybersecurity, autonomous transportation, or finance, where data shifts frequently.…
Recommender systems (RSs) are essential for e-commerce platforms to help meet the enormous needs of users. How to capture user interests and make accurate recommendations for users in heterogeneous e-commerce scenarios is still a continuous…