Search Results for author:
Found 17 papers, 14 papers with code
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition
In this study, we introduce a novel compact motion representation for video action recognition, named Optical Flow guided Feature (OFF), which enables the network to distill temporal information through a fast and robust approach.
Ranked #36 on
Action Recognition
on UCF101
Boosting up Scene Text Detectors with Guided CNN
Deep CNNs have achieved great success in text detection.
Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
Secondly, TSD significantly reduces the computations to run video action recognition with compressed frames on the cloud, while maintaining high recognition accuracies.
Learning Efficient Detector with Semi-supervised Adaptive Distillation
ADL enlarges the distillation loss for hard-to-learn and hard-to-mimic samples and reduces distillation loss for the dominant easy samples, enabling distillation to work on the single-stage detector first time, even if the student and the teacher are identical.
Data-Driven Neuron Allocation for Scale Aggregation Networks
The most informative output neurons in each block are preserved while others are discarded, and thus neurons for multiple scales are competitively and adaptively allocated.
Ranked #701 on
Image Classification
on ImageNet
Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid
To address this issue, we propose a novel Graph Reasoning Network (GRNet) on a Similarity Pyramid, which learns similarities between a query and a gallery cloth by using both global and local representations in multiple scales.
Ranked #4 on
Image Retrieval
on DeepFashion - Consumer-to-shop
(Rank-1 metric)
Geometry Normalization Networks for Accurate Scene Text Detection
Large geometry (e. g., orientation) variances are the key challenges in the scene text detection.
Ranked #10 on
Scene Text Detection
on ICDAR 2017 MLT
RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition
Theoretically, our proposed method, dubbed \emph{RobustScanner}, decodes individual characters with dynamic ratio between context and positional clues, and utilizes more positional ones when the decoding sequences with scarce context, and thus is robust and practical.
Context-Aware RCNN: A Baseline for Action Detection in Videos
In this work, we first empirically find the recognition accuracy is highly correlated with the bounding box size of an actor, and thus higher resolution of actors contributes to better performance.
Towards Impartial Multi-task Learning
Multi-task learning (MTL) has been widely used in representation learning.
Spatial Dual-Modality Graph Reasoning for Key Information Extraction
In order to roundly evaluate our proposed method as well as boost the future research, we release a new dataset named WildReceipt, which is collected and annotated tailored for the evaluation of key information extraction from document images of unseen templates in the wild.
Fourier Contour Embedding for Arbitrary-Shaped Text Detection
One of the main challenges for arbitrary-shaped text detection is to design a good text instance representation that allows networks to learn diverse text geometry variances.
Group Fisher Pruning for Practical Network Compression
Our method can be used to prune any structures including those with coupled channels.
Ranked #4 on
Network Pruning
on ImageNet
Vision Transformer with Progressive Sampling
As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image classification, by simply splitting images into tokens with a fixed length, and employing transformers to learn relations between these tokens.
MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding
We present MMOCR-an open-source toolbox which provides a comprehensive pipeline for text detection and recognition, as well as their downstream tasks such as named entity recognition and key information extraction.
Pseudo-mask Matters in Weakly-supervised Semantic Segmentation
For these matters, we propose the following designs to push the performance to new state-of-art: (i) Coefficient of Variation Smoothing to smooth the CAMs adaptively; (ii) Proportional Pseudo-mask Generation to project the expanded CAMs to pseudo-mask based on a new metric indicating the importance of each class on each location, instead of the scores trained from binary classifiers.
Ranked #27 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation
So we try to improve WSSS in the aspect of noise mitigation.
Ranked #23 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
