# Suppressing Uncertainties for Large-Scale Facial Expression Recognition

Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators.

57
0.44 stars / hour

# Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport

24 Jun 2021

In this paper, we propose a novel architecture, Temporal Routing Adaptor (TRA), to empower existing stock prediction models with the ability to model multiple stock trading patterns.

6,438
0.43 stars / hour

# PnP-DETR: Towards Efficient Visual Analysis with Transformers

15 Sep 2021

Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result.

39
0.39 stars / hour

# Anchor DETR: Query Design for Transformer-Based Detector

15 Sep 2021

Thanks to the query design and the attention variant, the proposed detector that we called Anchor DETR, can achieve better performance and run faster than the DETR with 10$\times$ fewer training epochs.

43
0.38 stars / hour

# Recurrent Multi-view Alignment Network for Unsupervised Surface Registration

Learning non-rigid registration in an end-to-end manner is challenging due to the inherent high degrees of freedom and the lack of labeled training data.

68
0.36 stars / hour

# Constant Curvature Graph Convolutional Networks

Interest has been rising lately towards methods representing data in non-Euclidean spaces, e. g. hyperbolic or spherical, that provide specific inductive biases useful for certain real-world data properties, e. g. scale-free, hierarchical or cyclical.

43
0.35 stars / hour

# Benchmarking the Spectrum of Agent Capabilities

14 Sep 2021

We hope that Crafter will accelerate research progress by quickly evaluating a wide spectrum of abilities.

103
0.33 stars / hour

# Learning to Prompt for Vision-Language Models

2 Sep 2021

It shifts from the tradition of using images and discrete labels for learning a fixed set of weights, seen as visual concepts, to aligning images and raw text for two separate encoders.

106
0.33 stars / hour

# Resolution-robust Large Mask Inpainting with Fourier Convolutions

15 Sep 2021

We find that one of the main reasons for that is the lack of an effective receptive field in both the inpainting network and the loss function.

26
0.32 stars / hour

# Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification

10 Feb 2020

Second, given cross-modality unpaired-images of a person, our method can generate cross-modality paired images from exchanged images.

103
0.29 stars / hour