Search Results for author:
Found 22 papers, 13 papers with code
DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework
We also introduce Kubric-NK, a new benchmark for evaluating optical flow methods with input resolutions ranging from 1K to 8K.
Ranked #1 on
Optical Flow Estimation
on Sintel-final
Video-Language Alignment via Spatio-Temporal Graph Transformer
In this paper, we propose a novel Spatio-Temporal Graph Transformer module to uniformly learn spatial and temporal contexts for video-language alignment pre-training (dubbed STGT).
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 #7 on
Optical Flow Estimation
on KITTI 2015
Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge Graph
We then craft a mixed-context reasoning module based on the multi-layer perceptron (MLP) to learn the unified representations of inter-quadruples for ECE while accomplishing temporal knowledge reasoning.
Arbitrary Time Information Modeling via Polynomial Approximation for Temporal Knowledge Graph Embedding
Distinguished from traditional knowledge graphs (KGs), temporal knowledge graphs (TKGs) must explore and reason over temporally evolving facts adequately.
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).
LayoutFormer: Hierarchical Text Detection Towards Scene Text Understanding
Existing scene text detectors generally focus on accurately detecting single-level (i. e. word-level line-level or paragraph-level) text entities without exploring the relationships among different levels of text entities.
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.
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.
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).
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.
GiT: Graph Interactive Transformer for Vehicle Re-identification
In the macro view, a list of GiT blocks are stacked to build a vehicle re-identification model, in where graphs are to extract discriminative local features within patches and transformers are to extract robust global features among patches.
Ranked #2 on
Vehicle Re-Identification
on VehicleID Small
(mAP metric)
Two-Stage Copy-Move Forgery Detection with Self Deep Matching and Proposal SuperGlue
The first stage is a backbone self deep matching network, and the second stage is named as Proposal SuperGlue.
Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification
Secondly, a novel pyramidal graph network (PGN) is designed to comprehensively explore the spatial significance of feature maps at multiple scales.
Ranked #3 on
Vehicle Re-Identification
on VehicleID Small
(mAP metric)
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.
AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance.
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision
Action recognition in videos has attracted a lot of attention in the past decade.
Adversarial Learning for Image Forensics Deep Matching with Atrous Convolution
Constrained image splicing detection and localization (CISDL) is a newly proposed challenging task for image forensics, which investigates two input suspected images and identifies whether one image has suspected regions pasted from the other.
