Search Results for author:
Found 26 papers, 11 papers with code
RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation
Extracting motion information from videos with optical flow estimation is vital in multiple practical robot applications.
Ranked #6 on
Optical Flow Estimation
on KITTI 2015
Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling
Specifically, we propose an innovative reading-order estimation module (REM) that extracts reading-order information from the initial text boundary generated by an initial boundary module (IBM).
InterFormer: Interactive Local and Global Features Fusion for Automatic Speech Recognition
To address these issues, this paper proposes InterFormer for interactive local and global features fusion to learn a better representation for ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding
The experimental results show that ASCD significantly improves the performance by leveraging both the acoustic and semantic information cooperatively.
Unsupervised Multi-view Pedestrian Detection
1) Firstly, Semantic-aware Iterative Segmentation (SIS) is proposed to extract unsupervised representations of multi-view images, which are converted into 2D pedestrian masks as pseudo labels, via our proposed iterative PCA and zero-shot semantic classes from vision-language models.
VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision
Firstly, we propose a self-supervised Vision-Language Semantic (VLS) segmentation method, which learns both fully-supervised pedestrian detection and contextual segmentation via self-generated explicit labels of semantic classes by vision-language models.
Ranked #5 on
Pedestrian Detection
on Caltech
Learning Correction Filter via Degradation-Adaptive Regression for Blind Single Image Super-Resolution
Instead of assuming degradation are spatially invariant across the whole image, we learn correction filters to adjust degradations to known degradations in a spatially variant way by a novel linearly-assembled pixel degradation-adaptive regression module (DARM).
Arbitrary Shape Text Detection via Segmentation with Probability Maps
To be concrete, we adopt a Sigmoid Alpha Function (SAF) to transfer the distances between boundaries and their inside pixels to a probability map.
Boosting Multi-Modal E-commerce Attribute Value Extraction via Unified Learning Scheme and Dynamic Range Minimization
2) Secondly, a text-guided information range minimization method is proposed to adaptively encode descriptive parts of each modality into an identical space with a powerful pretrained linguistic model.
Arbitrary Shape Text Detection via Boundary Transformer
In our method, we explicitly model the text boundary via an innovative iterative boundary transformer in a coarse-to-fine manner.
Graph Fusion Network for Multi-Oriented Object Detection
Then, we propose a graph-based fusion network via Graph Convolutional Network (GCN) to learn to reason and fuse the detection boxes for generating final instance boxes.
Open-set Text Recognition via Character-Context Decoupling
Contextual information can be decomposed into temporal information and linguistic information.
Kernel Proposal Network for Arbitrary Shape Text Detection
In this paper, we propose an innovative Kernel Proposal Network (dubbed KPN) for arbitrary shape text detection.
Towards Open-Set Text Recognition via Label-to-Prototype Learning
Scene text recognition is a popular topic and extensively used in the industry.
Learning Aligned Cross-Modal Representation for Generalized Zero-Shot Classification
Learning a common latent embedding by aligning the latent spaces of cross-modal autoencoders is an effective strategy for Generalized Zero-Shot Classification (GZSC).
Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition
To tackle the above problems, we propose a new non-autoregressive transformer with a unified bidirectional decoder (NAT-UBD), which can simultaneously utilize left-to-right and right-to-left contexts.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection
In this work, we propose a novel adaptive boundary proposal network for arbitrary shape text detection, which can learn to directly produce accurate boundary for arbitrary shape text without any post-processing.
End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining
Second, we propose to predict the quadrilateral bounding box in the local region by regressing the four corners of the license plate to robustly detect oblique license plates.
RUArt: A Novel Text-Centered Solution for Text-Based Visual Question Answering
Text-based visual question answering (VQA) requires to read and understand text in an image to correctly answer a given question.
Optical Character Recognition
Optical Character Recognition (OCR)
+2
Mutual-Supervised Feature Modulation Network for Occluded Pedestrian Detection
These two branches are trained in a mutual-supervised way with full body annotations and visible body annotations, respectively.
Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
In this paper, we propose a novel unified relational reasoning graph network for arbitrary shape text detection.
Semantic Bilinear Pooling for Fine-Grained Recognition
Specifically, we design a generalized cross-entropy loss for the training of the proposed framework to fully exploit the semantic priors via considering the relevance between adjacent levels and enlarge the distance between samples of different coarse classes.
AdaDNNs: Adaptive Ensemble of Deep Neural Networks for Scene Text Recognition
Recognizing text in the wild is a really challenging task because of complex backgrounds, various illuminations and diverse distortions, even with deep neural networks (convolutional neural networks and recurrent neural networks).
A Multi-strategy Query Processing Approach for Biomedical Question Answering: USTB\_PRIR at BioASQ 2017 Task 5B
This paper describes the participation of USTB{\_}PRIR team in the 2017 BioASQ 5B on question answering, including document retrieval, snippet retrieval, and concept retrieval task.
Learning to Diversify via Weighted Kernels for Classifier Ensemble
In this paper, we argue that diversity, not direct diversity on samples but adaptive diversity with data, is highly correlated to ensemble accuracy, and we propose a novel technology for classifier ensemble, learning to diversify, which learns to adaptively combine classifiers by considering both accuracy and diversity.
Robust Text Detection in Natural Scene Images
Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks.
