Search Results for author: Haoxiang Li

Found 32 papers, 12 papers with code

Deployment Prior Injection for Run-time Calibratable Object Detection

no code implementations27 Feb 2024 Mo Zhou, Yiding Yang, Haoxiang Li, Vishal M. Patel, Gang Hua

With a strong alignment between the training and test distributions, object relation as a context prior facilitates object detection.

Object object-detection +1

Spiking-PhysFormer: Camera-Based Remote Photoplethysmography with Parallel Spike-driven Transformer

no code implementations7 Feb 2024 Mingxuan Liu, Jiankai Tang, Haoxiang Li, Jiahao Qi, Siwei Li, Kegang Wang, Yuntao Wang, Hong Chen

Additionally, the power consumption of the transformer block is reduced by a factor of 12. 2, while maintaining decent performance as PhysFormer and other ANN-based models.

UGG: Unified Generative Grasping

1 code implementation28 Nov 2023 Jiaxin Lu, Hao Kang, Haoxiang Li, Bo Liu, Yiding Yang, QiXing Huang, Gang Hua

Generation-based methods that generate grasping postures conditioned on the object can often produce diverse grasping, but they are insufficient for high grasping success due to lack of discriminative information.

Grasp Generation Object

Large Language Models are Zero Shot Hypothesis Proposers

no code implementations10 Nov 2023 Biqing Qi, Kaiyan Zhang, Haoxiang Li, Kai Tian, Sihang Zeng, Zhang-Ren Chen, BoWen Zhou

We subsequently evaluate the hypothesis generation capabilities of various top-tier instructed models in zero-shot, few-shot, and fine-tuning settings, including both closed and open-source LLMs.

Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance

no code implementations ICCV 2023 Lei Fan, Bo Liu, Haoxiang Li, Ying Wu, Gang Hua

First, prediction uncertainty should be separately quantified as confusion depicting inter-class uncertainties and ignorance identifying out-of-distribution samples.

Decision Making

SAM-Deblur: Let Segment Anything Boost Image Deblurring

1 code implementation5 Sep 2023 Siwei Li, Mingxuan Liu, Yating Zhang, Shu Chen, Haoxiang Li, Zifei Dou, Hong Chen

Image deblurring is a critical task in the field of image restoration, aiming to eliminate blurring artifacts.

Deblurring Image Deblurring +1

DDM-NET: End-to-end learning of keypoint feature Detection, Description and Matching for 3D localization

1 code implementation8 Dec 2022 Xiangyu Xu, Li Guan, Enrique Dunn, Haoxiang Li, Gang Hua

In this paper, we propose an end-to-end framework that jointly learns keypoint detection, descriptor representation and cross-frame matching for the task of image-based 3D localization.

Keypoint Detection

Boosted Dynamic Neural Networks

1 code implementation30 Nov 2022 Haichao Yu, Haoxiang Li, Gang Hua, Gao Huang, Humphrey Shi

To optimize the model, these prediction heads together with the network backbone are trained on every batch of training data.

Weakly-guided Self-supervised Pretraining for Temporal Activity Detection

1 code implementation26 Nov 2021 Kumara Kahatapitiya, Zhou Ren, Haoxiang Li, Zhenyu Wu, Michael S. Ryoo, Gang Hua

However, such pretrained models are not ideal for downstream detection, due to the disparity between the pretraining and the downstream fine-tuning tasks.

Action Detection Activity Detection +2

Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking

no code implementations CVPR 2021 Yiding Yang, Zhou Ren, Haoxiang Li, Chunluan Zhou, Xinchao Wang, Gang Hua

In this paper, we propose a novel online approach to learning the pose dynamics, which are independent of pose detections in current fame, and hence may serve as a robust estimation even in challenging scenarios including occlusion.

Multi-Person Pose Estimation Multi-Person Pose Estimation and Tracking +1

GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition

no code implementations ICCV 2021 Bo Liu, Haoxiang Li, Hao Kang, Gang Hua, Nuno Vasconcelos

A new learning algorithm is then proposed for GeometrIc Structure Transfer (GIST), with resort to a combination of loss functions that combine class-balanced and random sampling to guarantee that, while overfitting to the popular classes is restricted to geometric parameters, it is leveraged to transfer class geometry from popular to few-shot classes.

Transfer Learning

Semi-supervised Long-tailed Recognition using Alternate Sampling

no code implementations1 May 2021 Bo Liu, Haoxiang Li, Hao Kang, Nuno Vasconcelos, Gang Hua

A consistency loss has been introduced to limit the impact from unlabeled data while leveraging them to update the feature embedding.

Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition

no code implementations1 May 2021 Bo Liu, Haoxiang Li, Hao Kang, Gang Hua, Nuno Vasconcelos

It is shown that, unlike class-balanced sampling, this is an adversarial augmentation strategy.

Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas

no code implementations24 Mar 2021 Wei Wei, Li Guan, Yue Liu, Hao Kang, Haoxiang Li, Ying Wu, Gang Hua

By the proposed physical regularization, our method can generate HDRs which are not only visually appealing but also physically plausible.

HDR Reconstruction Single-shot HDR Reconstruction

Few-Shot Open-Set Recognition using Meta-Learning

1 code implementation CVPR 2020 Bo Liu, Hao Kang, Haoxiang Li, Gang Hua, Nuno Vasconcelos

It is argued that the classic softmax classifier is a poor solution for open-set recognition, since it tends to overfit on the training classes.

Classification General Classification +3

Any-Precision Deep Neural Networks

2 code implementations17 Nov 2019 Haichao Yu, Haoxiang Li, Honghui Shi, Thomas S. Huang, Gang Hua

When all layers are set to low-bits, we show that the model achieved accuracy comparable to dedicated models trained at the same precision.

Towards Physically Safe Reinforcement Learning under Supervision

no code implementations19 Jan 2019 Yinan Zhang, Devin Balkcom, Haoxiang Li

A weighted average of the supervisor and learned policies is used during trials, with a heavier weight initially on the supervisor, in order to allow safe and useful physical trials while the learned policy is still ineffective.

OpenAI Gym reinforcement-learning +2

Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias

no code implementations ECCV 2018 Rameswar Panda, Jianming Zhang, Haoxiang Li, Joon-Young Lee, Xin Lu, Amit K. Roy-Chowdhury

While machine learning approaches to visual emotion recognition offer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts.

Emotion Recognition

Active Object Perceiver: Recognition-guided Policy Learning for Object Searching on Mobile Robots

no code implementations30 Jul 2018 Xin Ye, Zhe Lin, Haoxiang Li, Shibin Zheng, Yezhou Yang

We study the problem of learning a navigation policy for a robot to actively search for an object of interest in an indoor environment solely from its visual inputs.

Object Object Recognition +1

The AdobeIndoorNav Dataset: Towards Deep Reinforcement Learning based Real-world Indoor Robot Visual Navigation

1 code implementation24 Feb 2018 Kaichun Mo, Haoxiang Li, Zhe Lin, Joon-Young Lee

Synthetic data suffers from domain gap to the real-world scenes while visual inputs rendered from 3D reconstructed scenes have undesired holes and artifacts.


Learning Dense Facial Correspondences in Unconstrained Images

no code implementations ICCV 2017 Ronald Yu, Shunsuke Saito, Haoxiang Li, Duygu Ceylan, Hao Li

To train such a network, we generate a massive dataset of synthetic faces with dense labels using renderings of a morphable face model with variations in pose, expressions, lighting, and occlusions.

Face Alignment Face Model

VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation

1 code implementation ICCV 2017 Chuang Gan, Yandong Li, Haoxiang Li, Chen Sun, Boqing Gong

Many seemingly distant annotations (e. g., semantic segmentation and visual question answering (VQA)) are inherently connected in that they reveal different levels and perspectives of human understandings about the same visual scenes --- and even the same set of images (e. g., of COCO).

Language Modelling Multiple-choice +4

A Multi-Level Contextual Model For Person Recognition in Photo Albums

no code implementations CVPR 2016 Haoxiang Li, Jonathan Brandt, Zhe Lin, Xiaohui Shen, Gang Hua

Our new framework enables efficient use of these complementary multi-level contextual cues to improve overall recognition rates on the photo album person recognition task, as demonstrated through state-of-the-art results on a challenging public dataset.

Person Recognition

Hierarchical-PEP Model for Real-World Face Recognition

no code implementations CVPR 2015 Haoxiang Li, Gang Hua

We apply the PEP model hierarchically to decompose a face image into face parts at different levels of details to build pose-invariant part-based face representations.

Face Recognition Face Verification

A Convolutional Neural Network Cascade for Face Detection

no code implementations CVPR 2015 Haoxiang Li, Zhe Lin, Xiaohui Shen, Jonathan Brandt, Gang Hua

To improve localization effectiveness, and reduce the number of candidates at later stages, we introduce a CNN-based calibration stage after each of the detection stages in the cascade.

Face Detection

Efficient Boosted Exemplar-based Face Detection

no code implementations CVPR 2014 Haoxiang Li, Zhe Lin, Jonathan Brandt, Xiaohui Shen, Gang Hua

Despite the fact that face detection has been studied intensively over the past several decades, the problem is still not completely solved.

Face Detection

Probabilistic Elastic Matching for Pose Variant Face Verification

no code implementations CVPR 2013 Haoxiang Li, Gang Hua, Zhe Lin, Jonathan Brandt, Jianchao Yang

By augmenting each feature with its location, a Gaussian mixture model (GMM) is trained to capture the spatialappearance distribution of all face images in the training corpus.

Face Recognition Face Verification

Cannot find the paper you are looking for? You can Submit a new open access paper.