Search Results for author: Kaiqi Huang

Found 56 papers, 25 papers with code

Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Models

no code implementations15 Jan 2024 Xingzhou Lou, Junge Zhang, Ziyan Wang, Kaiqi Huang, Yali Du

Through the use of pre-trained LMs and the elimination of the need for a ground-truth cost, our method enhances safe policy learning under a diverse set of human-derived free-form natural language constraints.

Reinforcement Learning (RL) Safe Reinforcement Learning

TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient

1 code implementation25 Dec 2023 Xingzhou Lou, Junge Zhang, Timothy J. Norman, Kaiqi Huang, Yali Du

We propose Topology-based multi-Agent Policy gradiEnt (TAPE) for both stochastic and deterministic MAPG methods.

See Your Heart: Psychological states Interpretation through Visual Creations

no code implementations11 Feb 2023 Likun Yang, Xiaokun Feng, Xiaotang Chen, Shiyu Zhang, Kaiqi Huang

Dataset analysis illustrates that SpyIn is not only able to support VEIT, but also more challenging compared with other captioning datasets.

Emotion Classification Image Captioning

PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination

1 code implementation16 Jan 2023 Xingzhou Lou, Jiaxian Guo, Junge Zhang, Jun Wang, Kaiqi Huang, Yali Du

We conduct experiments on the Overcooked environment, and evaluate the zero-shot human-AI coordination performance of our method with both behavior-cloned human proxies and real humans.

InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation

no code implementations5 Jan 2023 Fei He, Haoyang Zhang, Naiyu Gao, Jian Jia, Yanhu Shan, Xin Zhao, Kaiqi Huang

When using such a pair to predict an object instance on the current frame, not only the generated instance is automatically associated with its precursors on previous frames, but the model gets a good prior for predicting the same object.

Instance Segmentation Object +2

Learning Disentangled Label Representations for Multi-label Classification

no code implementations2 Dec 2022 Jian Jia, Fei He, Naiyu Gao, Xiaotang Chen, Kaiqi Huang

The specificity of the framework lies in a feature disentangle module, which contains learnable semantic queries and a Semantic Spatial Cross-Attention (SSCA) module.

Attribute Classification +6

DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models

no code implementations16 Oct 2022 Yueqin Yin, Lianghua Huang, Yu Liu, Kaiqi Huang

In this work, we first design a group of mechanisms to simulate generative artifacts of popular generators (i. e., GANs, autoregressive models, and diffusion models), given real images.

Image Generation Image Restoration

QueryProp: Object Query Propagation for High-Performance Video Object Detection

no code implementations22 Jul 2022 Fei He, Naiyu Gao, Jian Jia, Xin Zhao, Kaiqi Huang

The proposed QueryProp contains two propagation strategies: 1) query propagation is performed from sparse key frames to dense non-key frames to reduce the redundant computation on non-key frames; 2) query propagation is performed from previous key frames to the current key frame to improve feature representation by temporal context modeling.

Object object-detection +2

RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning

no code implementations2 Jun 2022 Hao Chen, Guangkai Yang, Junge Zhang, Qiyue Yin, Kaiqi Huang

Specifically, these methods do not explicitly utilize the relationship between agents and cannot adapt to different sizes of inputs.

Reinforcement Learning (RL) Relation +1

PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation

1 code implementation CVPR 2022 Naiyu Gao, Fei He, Jian Jia, Yanhu Shan, Haoyang Zhang, Xin Zhao, Kaiqi Huang

To overcome these limitations, we propose a unified framework for the DPS task by applying a dynamic convolution technique to both the PS and depth prediction tasks.

Depth Estimation Depth Prediction +2

Re-parameterizing Your Optimizers rather than Architectures

1 code implementation30 May 2022 Xiaohan Ding, Honghao Chen, Xiangyu Zhang, Kaiqi Huang, Jungong Han, Guiguang Ding

For the extreme simplicity of model structure, we focus on a VGG-style plain model and showcase that such a simple model trained with a RepOptimizer, which is referred to as RepOpt-VGG, performs on par with or better than the recent well-designed models.


SOTVerse: A User-defined Task Space of Single Object Tracking

no code implementations15 Apr 2022 Shiyu Hu, Xin Zhao, Kaiqi Huang

Single object tracking (SOT) research falls into a cycle -- trackers perform well on most benchmarks but quickly fail in challenging scenarios, causing researchers to doubt the insufficient data content and take more effort to construct larger datasets with more challenging situations.

Object Tracking

Split Semantic Detection in Sandplay Images

no code implementations2 Mar 2022 Xiaokun Feng, Xiaotang Chen, Jian Jia, Kaiqi Huang

Sandplay image, as an important psychoanalysis carrier, is a visual scene constructed by the client selecting and placing sand objects (e. g., sand, river, human figures, animals, vegetation, buildings, etc.).

Attribute Dimensionality Reduction

Global Instance Tracking: Locating Target More Like Humans

1 code implementation26 Feb 2022 Shiyu Hu, Xin Zhao, Lianghua Huang, Kaiqi Huang

Finally, we design a scientific evaluation procedure using human capabilities as the baseline to judge tracking intelligence.

Decision Making Visual Tracking

AI in Human-computer Gaming: Techniques, Challenges and Opportunities

no code implementations15 Nov 2021 Qiyue Yin, Jun Yang, Kaiqi Huang, Meijing Zhao, Wancheng Ni, Bin Liang, Yan Huang, Shu Wu, Liang Wang

Through this survey, we 1) compare the main difficulties among different kinds of games and the corresponding techniques utilized for achieving professional human level AIs; 2) summarize the mainstream frameworks and techniques that can be properly relied on for developing AIs for complex human-computer gaming; 3) raise the challenges or drawbacks of current techniques in the successful AIs; and 4) try to point out future trends in human-computer gaming AIs.

Decision Making

Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition

no code implementations ICCV 2021 Jian Jia, Xiaotang Chen, Kaiqi Huang

To fully exploit inter-image relations and aggregate human prior in the model learning process, we construct a Spatial and Semantic Consistency (SSC) framework that consists of two complementary regularizations to achieve spatial and semantic consistency for each attribute.

Attribute Pedestrian Attribute Recognition

Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting

1 code implementation8 Jul 2021 Jian Jia, Houjing Huang, Xiaotang Chen, Kaiqi Huang

Second, based on the proposed definition, we expose the limitations of the existing datasets, which violate the academic norm and are inconsistent with the essential requirement of practical industry application.

Attribute Pedestrian Attribute Recognition

Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning

no code implementations9 Apr 2021 Wenzhen Huang, Qiyue Yin, Junge Zhang, Kaiqi Huang

More specifically, we evaluate the effect of an imaginary transition by calculating the change of the loss computed on the real samples when we use the transition to train the action-value and policy functions.

Model-based Reinforcement Learning reinforcement-learning +1

Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation

no code implementations28 Sep 2020 Naiyu Gao, Yanhu Shan, Xin Zhao, Kaiqi Huang

Panoptic segmentation (PS) is a complex scene understanding task that requires providing high-quality segmentation for both thing objects and stuff regions.

Instance Segmentation Panoptic Segmentation +2

Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Method

2 code implementations25 May 2020 Jian Jia, Houjing Huang, Wenjie Yang, Xiaotang Chen, Kaiqi Huang

Despite various methods are proposed to make progress in pedestrian attribute recognition, a crucial problem on existing datasets is often neglected, namely, a large number of identical pedestrian identities in train and test set, which is not consistent with practical application.

Attribute Pedestrian Attribute Recognition +1

GlobalTrack: A Simple and Strong Baseline for Long-term Tracking

1 code implementation18 Dec 2019 Lianghua Huang, Xin Zhao, Kaiqi Huang

Specifically, we propose GlobalTrack, a pure global instance search based tracker that makes no assumption on the temporal consistency of the target's positions and scales.

Instance Search

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

2 code implementations ICCV 2019 Naiyu Gao, Yanhu Shan, Yupei Wang, Xin Zhao, Yinan Yu, Ming Yang, Kaiqi Huang

Moreover, incorporating with the learned affinity pyramid, a novel cascaded graph partition module is presented to sequentially generate instances from coarse to fine.

Instance Segmentation Segmentation +1

Point Cloud Super Resolution with Adversarial Residual Graph Networks

1 code implementation arXiv:1908.02111 2019 Huikai Wu, Junge Zhang, Kaiqi Huang

The key idea of the proposed network is to exploit the local similarity of point cloud and the analogy between LR input and HR output.

Graphics Image and Video Processing

SparseMask: Differentiable Connectivity Learning for Dense Image Prediction

1 code implementation ICCV 2019 Huikai Wu, Junge Zhang, Kaiqi Huang

In this paper, we aim at automatically searching an efficient network architecture for dense image prediction.

FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation

12 code implementations28 Mar 2019 Huikai Wu, Junge Zhang, Kaiqi Huang, Kongming Liang, Yizhou Yu

Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity and memory footprint.

Semantic Segmentation

3D Object Detection Using Scale Invariant and Feature Reweighting Networks

no code implementations8 Jan 2019 Xin Zhao, Zhe Liu, Ruolan Hu, Kaiqi Huang

On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module.

3D Object Detection object-detection

GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild

2 code implementations29 Oct 2018 Lianghua Huang, Xin Zhao, Kaiqi Huang

(5) Finally, we develop a comprehensive platform for the tracking community that offers full-featured evaluation toolkits, an online evaluation server, and a responsive leaderboard.

Object Tracking Test

Discriminative Learning of Latent Features for Zero-Shot Recognition

1 code implementation CVPR 2018 Yan Li, Junge Zhang, Jian-Guo Zhang, Kaiqi Huang

In this work, we retrospect existing methods and demonstrate the necessity to learn discriminative representations for both visual and semantic instances of ZSL.

Zero-Shot Learning

Fast End-to-End Trainable Guided Filter

1 code implementation CVPR 2018 Huikai Wu, Shuai Zheng, Junge Zhang, Kaiqi Huang

To address the problem, we present a novel building block for FCNs, namely guided filtering layer, which is designed for efficiently generating a high-resolution output given the corresponding low-resolution one and a high-resolution guidance map.

Mixed Supervised Object Detection with Robust Objectness Transfer

no code implementations27 Feb 2018 Yan Li, Junge Zhang, Kaiqi Huang, Jian-Guo Zhang

Different from previous MSD methods that directly transfer the pre-trained object detectors from existing categories to new categories, we propose a more reasonable and robust objectness transfer approach for MSD.

Multiple Instance Learning Object +2

Deep Crisp Boundaries: From Boundaries to Higher-level Tasks

no code implementations8 Jan 2018 Yupei Wang, Xin Zhao, Yin Li, Kaiqi Huang

These ConvNet based edge detectors have approached human level performance on standard benchmarks.

Edge Detection Object Proposal Generation +2

Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification

no code implementations CVPR 2017 Dangwei Li, Xiaotang Chen, Zhang Zhang, Kaiqi Huang

It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc How to extract powerful features is a fundamental problem in ReID and is still an open problem today.

Person Identification Person Re-Identification +1

MSC: A Dataset for Macro-Management in StarCraft II

2 code implementations9 Oct 2017 Huikai Wu, Yanqi Zong, Junge Zhang, Kaiqi Huang

We also split MSC into training, validation and test set for the convenience of evaluation and comparison.

Management Starcraft +2

Deep Crisp Boundaries

no code implementations CVPR 2017 Yupei Wang, Xin Zhao, Kaiqi Huang

Edge detection had made significant progress with the help of deep Convolutional Networks (ConvNet).

Edge Detection Optical Flow Estimation

Beyond triplet loss: a deep quadruplet network for person re-identification

3 code implementations CVPR 2017 Weihua Chen, Xiaotang Chen, Jian-Guo Zhang, Kaiqi Huang

In particular, a quadruplet deep network using a margin-based online hard negative mining is proposed based on the quadruplet loss for the person ReID.

Person Re-Identification

GP-GAN: Towards Realistic High-Resolution Image Blending

2 code implementations21 Mar 2017 Huikai Wu, Shuai Zheng, Junge Zhang, Kaiqi Huang

Concretely, we propose Gaussian-Poisson Equation to formulate the high-resolution image blending problem, which is a joint optimization constrained by the gradient and color information.

Conditional Image Generation Generative Adversarial Network +1

A Large-scale Distributed Video Parsing and Evaluation Platform

no code implementations29 Nov 2016 Kai Yu, Yang Zhou, Da Li, Zhang Zhang, Kaiqi Huang

Visual surveillance systems have become one of the largest data sources of Big Visual Data in real world.

Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization

no code implementations17 Nov 2016 Kai Yu, Biao Leng, Zhang Zhang, Dangwei Li, Kaiqi Huang

Based on GoogLeNet, firstly, a set of mid-level attribute features are discovered by novelly designed detection layers, where a max-pooling based weakly-supervised object detection technique is used to train these layers with only image-level labels without the need of bounding box annotations of pedestrian attributes.

Attribute Clustering +5

A Multi-task Deep Network for Person Re-identification

no code implementations19 Jul 2016 Weihua Chen, Xiaotang Chen, Jian-Guo Zhang, Kaiqi Huang

Person re-identification (ReID) focuses on identifying people across different scenes in video surveillance, which is usually formulated as a binary classification task or a ranking task in current person ReID approaches.

Binary Classification Person Re-Identification

ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering

no code implementations CVPR 2016 Zhang Zhang, Kaiqi Huang, Tieniu Tan, Peipei Yang, Jun Li

For spectral embedding/clustering, it is still an open problem on how to construct an relation graph to reflect the intrinsic structures in data.

Clustering graph construction +5

Deep Aesthetic Quality Assessment with Semantic Information

no code implementations18 Apr 2016 Yueying Kao, Ran He, Kaiqi Huang

Human beings often assess the aesthetic quality of an image coupled with the identification of the image's semantic content.

Aesthetics Quality Assessment

A Richly Annotated Dataset for Pedestrian Attribute Recognition

2 code implementations23 Mar 2016 Dangwei Li, Zhang Zhang, Xiaotang Chen, Haibin Ling, Kaiqi Huang

RAP has in total 41, 585 pedestrian samples, each of which is annotated with 72 attributes as well as viewpoints, occlusions, body parts information.

Attribute Pedestrian Attribute Recognition

Query Adaptive Similarity Measure for RGB-D Object Recognition

no code implementations ICCV 2015 Yanhua Cheng, Rui Cai, Chi Zhang, Zhiwei Li, Xin Zhao, Kaiqi Huang, Yong Rui

The reasons are in two-fold: (1) existing similarity measures are sensitive to object pose and scale changes, as well as intra-class variations; and (2) effectively fusing RGB and depth cues is still an open problem.

Object Object Recognition +1

GRSA: Generalized Range Swap Algorithm for the Efficient Optimization of MRFs

no code implementations CVPR 2015 Kangwei Liu, Junge Zhang, Peipei Yang, Kaiqi Huang

al propose the range move algorithms, which are one of the most successful solvers to this problem.

An equalised global graphical model-based approach for multi-camera object tracking

1 code implementation12 Feb 2015 Weihua Chen, Lijun Cao, Xiaotang Chen, Kaiqi Huang

Non-overlapping multi-camera visual object tracking typically consists of two steps: single camera object tracking and inter-camera object tracking.

Object Visual Object Tracking

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