no code implementations • 25 Jan 2025 • Bingjun Luo, Jinpeng Wang, Wang Zewen, Junjie Zhu, Xibin Zhao
The proposed GCKD method consists of two main components.
1 code implementation • 19 Dec 2024 • Jinpeng Wang, Niu Lian, Jun Li, Yuting Wang, Yan Feng, Bin Chen, Yongbing Zhang, Shu-Tao Xia
We introduce S5VH, a Mamba-based video hashing model with an improved self-supervised learning paradigm.
1 code implementation • 20 Oct 2024 • Taolin Zhang, Jinpeng Wang, Hang Guo, Tao Dai, Bin Chen, Shu-Tao Xia
The historical samples are filtered from the testing data stream and serve to extract useful information from the target distribution, while the boosting samples are drawn from regional bootstrapping and capture the knowledge of the test sample itself.
no code implementations • 12 Oct 2024 • Taolin Zhang, Junwei Pan, Jinpeng Wang, Yaohua Zha, Tao Dai, Bin Chen, Ruisheng Luo, Xiaoxiang Deng, YuAn Wang, Ming Yue, Jie Jiang, Shu-Tao Xia
With recent advances in large language models (LLMs), there has been emerging numbers of research in developing Semantic IDs based on LLMs to enhance the performance of recommendation systems.
no code implementations • 29 Jul 2024 • Lei Huang, Weitao Li, Chenrui Zhang, Jinpeng Wang, Xianchun Yi, Sheng Chen
EXIT has been successfully deployed in the online homepage recommendation system of Meituan App, serving the main traffic.
1 code implementation • 24 May 2024 • Shiyu Qin, Jinpeng Wang, Yimin Zhou, Bin Chen, Tianci Luo, Baoyi An, Tao Dai, Shutao Xia, YaoWei Wang
Learned visual compression is an important and active task in multimedia.
1 code implementation • 22 May 2024 • Yuting Wang, Jinpeng Wang, Bin Chen, Tao Dai, Ruisheng Luo, Shu-Tao Xia
Given a text query, partially relevant video retrieval (PRVR) aims to retrieve untrimmed videos containing relevant moments.
1 code implementation • Proceedings of the AAAI Conference on Artificial Intelligence 2021 • Jinpeng Wang, Bin Chen, Qiang Zhang, Zaiqiao Meng, Shangsong Liang, Shu-Tao Xia
Deep quantization methods have shown high efficiency on large-scale image retrieval.
1 code implementation • 2 Apr 2024 • Yushen Li, Jinpeng Wang, Tao Dai, Jieming Zhu, Jun Yuan, Rui Zhang, Shu-Tao Xia
Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions.
1 code implementation • 28 Feb 2024 • Lanling Xu, Zhen Tian, Bingqian Li, Junjie Zhang, Jinpeng Wang, Mingchen Cai, Wayne Xin Zhao
The core idea of our approach is to conduct a sequence-level semantic fusion approach by better integrating global contexts.
no code implementations • 10 Jan 2024 • Lanling Xu, Junjie Zhang, Bingqian Li, Jinpeng Wang, Sheng Chen, Wayne Xin Zhao, Ji-Rong Wen
As for the use of LLMs as recommenders, we analyze the impact of public availability, tuning strategies, model architecture, parameter scale, and context length on recommendation results based on the classification of LLMs.
no code implementations • 10 Dec 2023 • Bingjun Luo, Zewen Wang, Jinpeng Wang, Junjie Zhu, Xibin Zhao, Yue Gao
Illumination variation has been a long-term challenge in real-world facial expression recognition(FER).
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
no code implementations • 10 Dec 2023 • Bingjun Luo, Haowen Wang, Jinpeng Wang, Junjie Zhu, Xibin Zhao, Yue Gao
With the strong robusticity on illumination variations, near-infrared (NIR) can be an effective and essential complement to visible (VIS) facial expression recognition in low lighting or complete darkness conditions.
Facial Expression Recognition
Facial Expression Recognition (FER)
no code implementations • 23 Nov 2023 • Shiyu Qin, Yimin Zhou, Jinpeng Wang, Bin Chen, Baoyi An, Tao Dai, Shu-Tao Xia
In this paper, we propose a progressive learning paradigm for transformer-based variable-rate image compression.
1 code implementation • 2 Nov 2023 • Yifan Du, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, Ji-Rong Wen
By conducting a comprehensive empirical study, we find that instructions focused on complex visual reasoning tasks are particularly effective in improving the performance of MLLMs on evaluation benchmarks.
1 code implementation • 8 Oct 2023 • Yuting Wang, Jinpeng Wang, Bin Chen, Ziyun Zeng, Shu-Tao Xia
Current PRVR methods adopt scanning-based clip construction to achieve explicit clip modeling, which is information-redundant and requires a large storage overhead.
1 code implementation • 23 Aug 2023 • Chenrui Zhang, Lin Liu, Jinpeng Wang, Chuyuan Wang, Xiao Sun, Hongyu Wang, Mingchen Cai
Moreover, to enhance stability of the prompt effect evaluation, we propose a novel prompt bagging method involving forward and backward thinking, which is superior to majority voting and is beneficial for both feedback and weight calculation in boosting.
1 code implementation • 22 Aug 2023 • Jinpeng Wang, Ziyun Zeng, Yunxiao Wang, Yuting Wang, Xingyu Lu, Tianxiang Li, Jun Yuan, Rui Zhang, Hai-Tao Zheng, Shu-Tao Xia
We propose MISSRec, a multi-modal pre-training and transfer learning framework for SR. On the user side, we design a Transformer-based encoder-decoder model, where the contextual encoder learns to capture the sequence-level multi-modal user interests while a novel interest-aware decoder is developed to grasp item-modality-interest relations for better sequence representation.
6 code implementations • 17 May 2023 • YiFan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, Ji-Rong Wen
Despite the promising progress on LVLMs, we find that LVLMs suffer from the hallucination problem, i. e. they tend to generate objects that are inconsistent with the target images in the descriptions.
no code implementations • 6 May 2023 • Minyi Zhao, Jinpeng Wang, Dongliang Liao, Yiru Wang, Huanzhong Duan, Shuigeng Zhou
On the one hand, standard retrieval systems are usually biased to common semantics and seldom exploit diversity-aware regularization in training, which makes it difficult to promote diversity by post-processing.
3 code implementations • ICCV 2023 • Yaohua Zha, Jinpeng Wang, Tao Dai, Bin Chen, Zhi Wang, Shu-Tao Xia
To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models.
3D Parameter-Efficient Fine-Tuning for Classification
Few-Shot 3D Point Cloud Classification
+1
1 code implementation • 21 Nov 2022 • Yuting Wang, Jinpeng Wang, Bin Chen, Ziyun Zeng, Shutao Xia
To capture video semantic information for better hashing learning, we adopt an encoder-decoder structure to reconstruct the video from its temporal-masked frames.
1 code implementation • 7 Feb 2022 • Jinpeng Wang, Bin Chen, Dongliang Liao, Ziyun Zeng, Gongfu Li, Shu-Tao Xia, Jin Xu
By performing Asymmetric-Quantized Contrastive Learning (AQ-CL) across views, HCQ aligns texts and videos at coarse-grained and multiple fine-grained levels.
1 code implementation • 7 Dec 2021 • Manlin Zhang, Jinpeng Wang, Andy J. Ma
By modelling static factors in a video as a random variable, the conditional distribution of each latent variable becomes shifted and scaled normal.
no code implementations • 28 Oct 2021 • Jinpeng Wang, Jieming Zhu, Xiuqiang He
The two-tower architecture has been widely applied for learning item and user representations, which is important for large-scale recommender systems.
1 code implementation • 26 Sep 2021 • Kelong Mao, Jieming Zhu, Jinpeng Wang, Quanyu Dai, Zhenhua Dong, Xi Xiao, Xiuqiang He
While many existing studies focus on the design of more powerful interaction encoders, the impacts of loss functions and negative sampling ratios have not yet been well explored.
Ranked #4 on
Collaborative Filtering
on Yelp2018
1 code implementation • 11 Sep 2021 • Jinpeng Wang, Ziyun Zeng, Bin Chen, Tao Dai, Shu-Tao Xia
The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems.
no code implementations • 11 Sep 2021 • Ziyun Zeng, Jinpeng Wang, Bin Chen, Tao Dai, Shu-Tao Xia, Zhi Wang
To improve fine-grained image hashing, we propose Pyramid Hybrid Pooling Quantization (PHPQ).
no code implementations • 6 Apr 2021 • Qiang Cui, Chenrui Zhang, Yafeng Zhang, Jinpeng Wang, Mingchen Cai
Specifically, in the long-term module, we learn the temporal periodic interest of daily granularity, then utilize intra-level attention to form long-term interest.
no code implementations • 1 Jan 2021 • Yuxi Xie, Danqing Huang, Jinpeng Wang, Chin-Yew Lin
Layout representation, which models visual elements in a canvas and their inter-relations, plays a crucial role in graphic design intelligence.
no code implementations • COLING 2020 • Feng Nie, Jinpeng Wang, Chin-Yew Lin
Large-scale datasets recently proposed for generation contain loosely corresponding data text pairs, where part of spans in text cannot be aligned to its incomplete paired input.
3 code implementations • 12 Sep 2020 • Jinpeng Wang, Yuting Gao, Ke Li, Jianguo Hu, Xinyang Jiang, Xiaowei Guo, Rongrong Ji, Xing Sun
Specifically, we construct a positive clip and a negative clip for each video.
2 code implementations • CVPR 2021 • Jinpeng Wang, Yuting Gao, Ke Li, Yiqi Lin, Andy J. Ma, Hao Cheng, Pai Peng, Feiyue Huang, Rongrong Ji, Xing Sun
Then we force the model to pull the feature of the distracting video and the feature of the original video closer, so that the model is explicitly restricted to resist the background influence, focusing more on the motion changes.
1 code implementation • 5 Aug 2020 • Jinpeng Wang, Yiqi Lin, Andy J. Ma
Self-supervised learning has shown great potentials in improving the deep learning model in an unsupervised manner by constructing surrogate supervision signals directly from the unlabeled data.
1 code implementation • 5 Aug 2020 • Jinpeng Wang, Yiqi Lin, Andy J. Ma, Pong C. Yuen
Without labelled data for network pretraining, temporal triplet is generated for each anchor video by using segment of the same or different time interval so as to enhance the capacity for temporal feature representation.
no code implementations • 6 Jan 2020 • Shuang Chen, Jinpeng Wang, Feng Jiang, Chin-Yew Lin
Existing state of the art neural entity linking models employ attention-based bag-of-words context model and pre-trained entity embeddings bootstrapped from word embeddings to assess topic level context compatibility.
Ranked #2 on
Entity Disambiguation
on AIDA-CoNLL
(Micro-F1 metric)
no code implementations • IJCNLP 2019 • Shuang Chen, Jinpeng Wang, Xiaocheng Feng, Feng Jiang, Bing Qin, Chin-Yew Lin
Recent neural models for data-to-text generation rely on massive parallel pairs of data and text to learn the writing knowledge.
no code implementations • WS 2019 • Feng Nie, Jinpeng Wang, Rong pan, Chin-Yew Lin
Data-to-text generation aims to generate descriptions given a structured input data (i. e., a table with multiple records).
no code implementations • ACL 2019 • Feng Nie, Jin-Ge Yao, Jinpeng Wang, Rong pan, Chin-Yew Lin
Recent neural language generation systems often \textit{hallucinate} contents (i. e., producing irrelevant or contradicted facts), especially when trained on loosely corresponding pairs of the input structure and text.
no code implementations • EMNLP 2018 • Longxu Dou, Guanghui Qin, Jinpeng Wang, Jin-Ge Yao, Chin-Yew Lin
Data2Text Studio is a platform for automated text generation from structured data.
no code implementations • CONLL 2018 • Feng Nie, Shuyan Zhou, Jing Liu, Jinpeng Wang, Chin-Yew Lin, Rong pan
The task of entity linking aims to identify concepts mentioned in a text fragments and link them to a reference knowledge base.
1 code implementation • EMNLP 2018 • Guanghui Qin, Jin-Ge Yao, Xuening Wang, Jinpeng Wang, Chin-Yew Lin
Previous work on grounded language learning did not fully capture the semantics underlying the correspondences between structured world state representations and texts, especially those between numerical values and lexical terms.
no code implementations • EMNLP 2018 • Feng Nie, Jinpeng Wang, Jin-Ge Yao, Rong pan, Chin-Yew Lin
Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data.
1 code implementation • 8 Sep 2018 • Feng Nie, Jinpeng Wang, Jin-Ge Yao, Rong pan, Chin-Yew Lin
Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data.
no code implementations • 15 Aug 2018 • Feng Nie, Hailin Chen, Jinpeng Wang, Jin-Ge Yao, Chin-Yew Lin, Rong pan
Recent neural models for data-to-document generation have achieved remarkable progress in producing fluent and informative texts.
no code implementations • IJCNLP 2017 • Jinpeng Wang, Yutai Hou, Jing Liu, Yunbo Cao, Chin-Yew Lin
We present in this paper a statistical framework that generates accurate and fluent product description from product attributes.