no code implementations • ECCV 2020 • Guangyi Chen, Yuhao Lu, Jiwen Lu, Jie Zhou
Experimental results demonstrate that our DCML method explores credible and valuable training data and improves the performance of unsupervised domain adaptation.
no code implementations • ECCV 2020 • Guangyi Chen, Yongming Rao, Jiwen Lu, Jie zhou
Specifically, we disentangle the video representation into the temporal coherence and motion parts and randomly change the scale of the temporal motion features as the adversarial noise.
1 code implementation • ACL 2022 • Xu Han, Guoyang Zeng, Weilin Zhao, Zhiyuan Liu, Zhengyan Zhang, Jie zhou, Jun Zhang, Jia Chao, Maosong Sun
In recent years, large-scale pre-trained language models (PLMs) containing billions of parameters have achieved promising results on various NLP tasks.
1 code implementation • ACL 2022 • Yikang Shen, Shawn Tan, Alessandro Sordoni, Peng Li, Jie zhou, Aaron Courville
We introduce a new model, the Unsupervised Dependency Graph Network (UDGN), that can induce dependency structures from raw corpora and the masked language modeling task.
no code implementations • ACL 2022 • Kunyuan Pang, Haoyu Zhang, Jie zhou, Ting Wang
In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems.
no code implementations • ACL 2022 • Hui Su, Weiwei Shi, Xiaoyu Shen, Zhou Xiao, Tuo ji, Jiarui Fang, Jie zhou
Large-scale pretrained language models have achieved SOTA results on NLP tasks.
no code implementations • Findings (ACL) 2022 • Xin Lv, Yankai Lin, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu, Peng Li, Jie zhou
In recent years, pre-trained language models (PLMs) have been shown to capture factual knowledge from massive texts, which encourages the proposal of PLM-based knowledge graph completion (KGC) models.
1 code implementation • Findings (ACL) 2022 • Zhexin Zhang, Yeshuang Zhu, Zhengcong Fei, Jinchao Zhang, Jie zhou
With the increasing popularity of online chatting, stickers are becoming important in our online communication.
no code implementations • Findings (ACL) 2022 • Le Tian, Houjin Yu, Zhou Xiao, Hui Su, Jie zhou
Prompt-based paradigm has shown its competitive performance in many NLP tasks.
no code implementations • ECCV 2020 • Liangliang Ren, Yangyang Song, Jiwen Lu, Jie zhou
Unlike most existing works that define room layout on a 2D image, we model the layout in 3D as a configuration of the camera and the room.
no code implementations • ECCV 2020 • Yu Zheng, Danyang Zhang, Sinan Xie, Jiwen Lu, Jie zhou
In this paper, we propose a Rotation-robust Intersection over Union ($ extit{RIoU}$) for 3D object detection, which aims to jointly learn the overlap of rotated bounding boxes.
no code implementations • ECCV 2020 • Ziwei Wang, Quan Zheng, Jiwen Lu, Jie zhou
n this paper, we propose a Deep Hashing method with Active Pairwise Supervision(DH-APS).
1 code implementation • EMNLP 2021 • Yuan YAO, Jiaju Du, Yankai Lin, Peng Li, Zhiyuan Liu, Jie zhou, Maosong Sun
Existing relation extraction (RE) methods typically focus on extracting relational facts between entity pairs within single sentences or documents.
no code implementations • Findings (EMNLP) 2021 • Lei Shen, Jinchao Zhang, Jiao Ou, Xiaofang Zhao, Jie zhou
To address the above issues, we propose a dual-generative model, Dual-Emp, to simultaneously construct the emotional consensus and utilize some external unpaired data.
no code implementations • CCL 2021 • Shan Wang, Jie zhou
“欺骗是一种常见的社会现象, 但对欺骗类动词的研究十分有限。本文筛选“欺骗”类动词的单句并对其进行大规模的句法依存和语义依存分析。研究显示,“欺骗”类动词在句中作为从属词时, 可作为不同的句法成分和语义角色, 同时此类动词在句法功能上表现出高度的相似性。作为支配词的“欺骗”类动词, 承担不同句法功能时, 表现出不同的句法共现模式。语义上, 本文详细描述、解释了该类动词在语义密度、主客体角色、情境角色和事件关系等维度的语义依存特点。“欺骗”类动词的句法语义虽具有多样性, 但主要的句型为主谓宾句式, 而该句式中最常用的语义搭配模式是施事对涉事进行欺骗行为, 并对涉事产生影响。本研究结合依存语法和框架语义学, 融合定量统计和定性分析探究欺骗类动词的句法语义, 深化了对欺骗行为言语线索以及言说动词的研究。”
no code implementations • EMNLP 2020 • Hui Su, Xiaoyu Shen, Zhou Xiao, Zheng Zhang, Ernie Chang, Cheng Zhang, Cheng Niu, Jie zhou
In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots.
no code implementations • ECCV 2020 • Wenzhao Zheng, Jiwen Lu, Jie zhou
We employ a metric model and a layout encoder to map the RGB images and the ground-truth layouts to the embedding space, respectively, and a layout decoder to map the embeddings to the corresponding layouts, where the whole framework is trained in an end-to-end manner.
no code implementations • EMNLP 2020 • Xiuyi Chen, Fandong Meng, Peng Li, Feilong Chen, Shuang Xu, Bo Xu, Jie zhou
Here, we deal with these issues on two aspects: (1) We enhance the prior selection module with the necessary posterior information obtained from the specially designed Posterior Information Prediction Module (PIPM); (2) We propose a Knowledge Distillation Based Training Strategy (KDBTS) to train the decoder with the knowledge selected from the prior distribution, removing the exposure bias of knowledge selection.
1 code implementation • 19 May 2022 • Yunpeng Zhang, Zheng Zhu, Wenzhao Zheng, JunJie Huang, Guan Huang, Jie zhou, Jiwen Lu
Specifically, BEVerse first performs shared feature extraction and lifting to generate 4D BEV representations from multi-timestamp and multi-view images.
1 code implementation • 9 May 2022 • Chengkun Wang, Wenzhao Zheng, Zheng Zhu, Jie zhou, Jiwen Lu
This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images.
1 code implementation • ACL 2022 • Yunlong Liang, Fandong Meng, Jinan Xu, Yufeng Chen, Jie zhou
Neural Chat Translation (NCT) aims to translate conversational text into different languages.
no code implementations • ICCV 2021 • Zheng Zhu, Xianda Guo, Tian Yang, JunJie Huang, Jiankang Deng, Guan Huang, Dalong Du, Jiwen Lu, Jie zhou
In this paper, we contribute a new benchmark for Gait REcognition in the Wild (GREW).
no code implementations • 2 May 2022 • Zhe Cui, Jianjiang Feng, Jie zhou
Compared with contact-based fingerprint acquisition techniques, contactless acquisition has the advantages of less skin distortion, larger fingerprint area, and hygienic acquisition.
1 code implementation • 2 May 2022 • Jiangnan Li, Fandong Meng, Zheng Lin, Rui Liu, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou
Conversational Causal Emotion Entailment aims to detect causal utterances for a non-neutral targeted utterance from a conversation.
1 code implementation • 1 May 2022 • Jiaju Lin, Qin Chen, Jie zhou, Jian Jin, Liang He
Implicit event argument extraction (EAE) aims to identify arguments that could scatter over the document.
1 code implementation • 25 Apr 2022 • Linzhi Wu, Pengjun Xie, Jie zhou, Meishan Zhang, Chunping Ma, Guangwei Xu, Min Zhang
Prior research has mainly resorted to heuristic rule-based constraints to reduce the noise for specific self-augmentation methods individually.
1 code implementation • 24 Apr 2022 • Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou
Firstly, we discover that the success of magnitude pruning can be attributed to the preserved pre-training performance, which correlates with the downstream transferability.
no code implementations • 21 Apr 2022 • Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Dalong Du, Jiwen Lu, Jie zhou
For a comprehensive evaluation of face matchers, three recognition tasks are performed under standard, masked and unbiased settings, respectively.
no code implementations • 19 Apr 2022 • Siyu Lai, Zhen Yang, Fandong Meng, Xue Zhang, Yufeng Chen, Jinan Xu, Jie zhou
Generating adversarial examples for Neural Machine Translation (NMT) with single Round-Trip Translation (RTT) has achieved promising results by releasing the meaning-preserving restriction.
no code implementations • 12 Apr 2022 • Yu Zheng, Yueqi Duan, Jiwen Lu, Jie zhou, Qi Tian
A bathtub in a library, a sink in an office, a bed in a laundry room -- the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar objects.
1 code implementation • 7 Apr 2022 • Yi Wei, Linqing Zhao, Wenzhao Zheng, Zheng Zhu, Yongming Rao, Guan Huang, Jiwen Lu, Jie zhou
In this paper, we propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras.
1 code implementation • 7 Apr 2022 • Jinglin Xu, Yongming Rao, Xumin Yu, Guangyi Chen, Jie zhou, Jiwen Lu
Most existing action quality assessment methods rely on the deep features of an entire video to predict the score, which is less reliable due to the non-transparent inference process and poor interpretability.
no code implementations • IEEE Transactions on Image Processing 2022 • Wencheng Zhu, Yucheng Han, Jiwen Lu, Jie zhou
Then, we construct a temporal graph by using the aggregated representations of spatial graphs.
Ranked #1 on
Video Summarization
on TvSum
no code implementations • ACL 2022 • Pei Ke, Hao Zhou, Yankai Lin, Peng Li, Jie zhou, Xiaoyan Zhu, Minlie Huang
Existing reference-free metrics have obvious limitations for evaluating controlled text generation models.
1 code implementation • 28 Mar 2022 • Borui Zhang, Wenzhao Zheng, Jie zhou, Jiwen Lu
This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and explainable similarity measure between images.
1 code implementation • 28 Mar 2022 • Yi Wei, Zibu Wei, Yongming Rao, Jiaxin Li, Jie zhou, Jiwen Lu
In this paper, we propose the LiDAR Distillation to bridge the domain gap induced by different LiDAR beams for 3D object detection.
1 code implementation • 26 Mar 2022 • Muheng Li, Lei Chen, Yueqi Duan, Zhilan Hu, Jianjiang Feng, Jie zhou, Jiwen Lu
The generated text prompts are paired with corresponding video clips, and together co-train the text encoder and the video encoder via a contrastive approach.
Ranked #1 on
Action Segmentation
on 50 Salads
1 code implementation • 25 Mar 2022 • Tianpei Gu, Guangyi Chen, Junlong Li, Chunze Lin, Yongming Rao, Jie zhou, Jiwen Lu
Human behavior has the nature of indeterminacy, which requires the pedestrian trajectory prediction system to model the multi-modality of future motion states.
no code implementations • 23 Mar 2022 • Jiaan Wang, Fandong Meng, Duo Zheng, Yunlong Liang, Zhixu Li, Jianfeng Qu, Jie zhou
Cross-lingual summarization is the task of generating a summary in one language (e. g., English) for the given document(s) in a different language (e. g., Chinese).
no code implementations • 16 Mar 2022 • Duo Zheng, Fandong Meng, Qingyi Si, Hairun Fan, Zipeng Xu, Jie zhou, Fangxiang Feng, Xiaojie Wang
Visual dialog has witnessed great progress after introducing various vision-oriented goals into the conversation, especially such as GuessWhich and GuessWhat, where the only image is visible by either and both of the questioner and the answerer, respectively.
1 code implementation • Findings (ACL) 2022 • Yujia Qin, Jiajie Zhang, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie zhou
We experiment ELLE with streaming data from 5 domains on BERT and GPT.
2 code implementations • 10 Mar 2022 • Xiuwei Xu, Yifan Wang, Yu Zheng, Yongming Rao, Jie zhou, Jiwen Lu
In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i. e. annotations of object centers).
1 code implementation • ACL 2022 • Yunlong Liang, Fandong Meng, Chulun Zhou, Jinan Xu, Yufeng Chen, Jinsong Su, Jie zhou
The goal of the cross-lingual summarization (CLS) is to convert a document in one language (e. g., English) to a summary in another one (e. g., Chinese).
no code implementations • 7 Mar 2022 • Leyang Cui, Fandong Meng, Yijin Liu, Jie zhou, Yue Zhang
Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-world practice, especially in multi-turn settings.
1 code implementation • ACL 2022 • Songming Zhang, Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jian Liu, Jie zhou
Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e. g., token frequency or mutual information).
1 code implementation • 2 Mar 2022 • Duzhen Zhang, Zhen Yang, Fandong Meng, Xiuyi Chen, Jie zhou
Causal Emotion Entailment (CEE) aims to discover the potential causes behind an emotion in a conversational utterance.
1 code implementation • ACL 2022 • Yunlong Liang, Fandong Meng, Jinan Xu, Yufeng Chen, Jie zhou
In this work, we introduce a new task named Multimodal Chat Translation (MCT), aiming to generate more accurate translations with the help of the associated dialogue history and visual context.
no code implementations • ACL 2022 • Chulun Zhou, Fandong Meng, Jie zhou, Min Zhang, Hongji Wang, Jinsong Su
Most dominant neural machine translation (NMT) models are restricted to make predictions only according to the local context of preceding words in a left-to-right manner.
1 code implementation • 11 Feb 2022 • Jiaan Wang, Fandong Meng, Ziyao Lu, Duo Zheng, Zhixu Li, Jianfeng Qu, Jie zhou
We present ClidSum, a benchmark dataset for building cross-lingual summarization systems on dialogue documents.
no code implementations • 29 Jan 2022 • Fei Gao, Peng Geng, Jiaqi Guo, YuAn Liu, Dingfeng Guo, Yabo Su, Jie zhou, Xiao Wei, Jin Li, Xu Liu
We introduce ApolloRL, an open platform for research in reinforcement learning for autonomous driving.
no code implementations • 14 Jan 2022 • Yong Shan, Jinchao Zhang, Zekang Li, Yang Feng, Jie zhou
Previous researches on dialogue system assessment usually focus on the quality evaluation (e. g. fluency, relevance, etc) of responses generated by the chatbots, which are local and technical metrics.
1 code implementation • 12 Jan 2022 • Bin Xia, Yapeng Tian, Yucheng Hang, Wenming Yang, Qingmin Liao, Jie zhou
To improve matching efficiency, we design a novel Embedded PatchMacth scheme with random samples propagation, which involves end-to-end training with asymptotic linear computational cost to the input size.
1 code implementation • 11 Jan 2022 • Bin Xia, Yucheng Hang, Yapeng Tian, Wenming Yang, Qingmin Liao, Jie zhou
To demonstrate the effectiveness of ENLCA, we build an architecture called Efficient Non-Local Contrastive Network (ENLCN) by adding a few of our modules in a simple backbone.
no code implementations • 23 Dec 2021 • Jun Wan, Hui Xi, Jie zhou, Zhihui Lai, Witold Pedrycz, Xu Wang, Hang Sun
We show that by integrating the BALI fields and SCPA model into a novel self-calibrated pose attention network, more facial prior knowledge can be learned and the detection accuracy and robustness of our method for faces with large poses and heavy occlusions have been improved.
2 code implementations • 22 Dec 2021 • Liang Pan, Tong Wu, Zhongang Cai, Ziwei Liu, Xumin Yu, Yongming Rao, Jiwen Lu, Jie zhou, Mingye Xu, Xiaoyuan Luo, Kexue Fu, Peng Gao, Manning Wang, Yali Wang, Yu Qiao, Junsheng Zhou, Xin Wen, Peng Xiang, Yu-Shen Liu, Zhizhong Han, Yuanjie Yan, Junyi An, Lifa Zhu, Changwei Lin, Dongrui Liu, Xin Li, Francisco Gómez-Fernández, Qinlong Wang, Yang Yang
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
1 code implementation • 17 Dec 2021 • An Tao, Yueqi Duan, He Wang, Ziyi Wu, Pengliang Ji, Haowen Sun, Jie zhou, Jiwen Lu
It results in a serious issue of lagged gradient, making the learned attack at the current step ineffective due to the architecture changes afterward.
no code implementations • 14 Dec 2021 • Lei LI, Yankai Lin, Xuancheng Ren, Guangxiang Zhao, Peng Li, Jie zhou, Xu sun
As many fine-tuned pre-trained language models~(PLMs) with promising performance are generously released, investigating better ways to reuse these models is vital as it can greatly reduce the retraining computational cost and the potential environmental side-effects.
1 code implementation • 2 Dec 2021 • Yongming Rao, Wenliang Zhao, Guangyi Chen, Yansong Tang, Zheng Zhu, Guan Huang, Jie zhou, Jiwen Lu
In this work, we present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP.
1 code implementation • 29 Nov 2021 • Xumin Yu, Lulu Tang, Yongming Rao, Tiejun Huang, Jie zhou, Jiwen Lu
Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers.
Ranked #8 on
3D Point Cloud Classification
on ScanObjectNN
1 code implementation • 12 Nov 2021 • Yusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Huadong Wang, Kaiyue Wen, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou, Maosong Sun, Jie zhou
To explore whether we can improve PT via prompt transfer, we empirically investigate the transferability of soft prompts across different downstream tasks and PLMs in this work.
Natural Language Understanding
Pretrained Language Models
+1
no code implementations • 24 Oct 2021 • Jianglin Lu, Hailing Wang, Jie zhou, Mengfan Yan, Jiajun Wen
Recently, deep hashing methods have been widely used in image retrieval task.
1 code implementation • 15 Oct 2021 • Yujia Qin, Xiaozhi Wang, Yusheng Su, Yankai Lin, Ning Ding, Jing Yi, Weize Chen, Zhiyuan Liu, Juanzi Li, Lei Hou, Peng Li, Maosong Sun, Jie zhou
In the experiments, we study diverse few-shot NLP tasks and surprisingly find that in a 250-dimensional subspace found with 100 tasks, by only tuning 250 free parameters, we can recover 97% and 83% of the full prompt tuning performance for 100 seen tasks (using different training data) and 20 unseen tasks, respectively, showing great generalization ability of the found intrinsic task subspace.
1 code implementation • EMNLP 2021 • Wenkai Yang, Yankai Lin, Peng Li, Jie zhou, Xu sun
Motivated by this observation, we construct a word-based robustness-aware perturbation to distinguish poisoned samples from clean samples to defend against the backdoor attacks on natural language processing (NLP) models.
1 code implementation • EMNLP 2021 • Shaopeng Lai, Ante Wang, Fandong Meng, Jie zhou, Yubin Ge, Jiali Zeng, Junfeng Yao, Degen Huang, Jinsong Su
Dominant sentence ordering models can be classified into pairwise ordering models and set-to-sequence models.
1 code implementation • 11 Oct 2021 • Zhen Yang, Fandong Meng, Yingxue Zhang, Ernan Li, Jie zhou
To break this limitation, we create a benchmark data set for TS, called \emph{WeTS}, which contains golden corpus annotated by expert translators on four translation directions.
1 code implementation • NeurIPS 2021 • Deli Chen, Yankai Lin, Guangxiang Zhao, Xuancheng Ren, Peng Li, Jie zhou, Xu sun
The class imbalance problem, as an important issue in learning node representations, has drawn increasing attention from the community.
1 code implementation • Findings (ACL) 2022 • Zhengyan Zhang, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie zhou
In this work, we study the computational patterns of FFNs and observe that most inputs only activate a tiny ratio of neurons of FFNs.
no code implementations • 1 Oct 2021 • Xianggen Liu, Pengyong Li, Fandong Meng, Hao Zhou, Huasong Zhong, Jie zhou, Lili Mou, Sen Song
The key idea is to integrate powerful neural networks into metaheuristics (e. g., simulated annealing, SA) to restrict the search space in discrete optimization.
no code implementations • 29 Sep 2021 • Han Xiao, Ziwei Wang, Jiwen Lu, Jie zhou
In this paper, we propose a Shapley value based operation contribution evaluation method (Shapley-NAS) for neural architecture search.
1 code implementation • 26 Sep 2021 • Cheng Ma, Yongming Rao, Jiwen Lu, Jie zhou
Firstly, we propose SPSR with gradient guidance (SPSR-G) by exploiting gradient maps of images to guide the recovery in two aspects.
1 code implementation • EMNLP 2021 • Lei LI, Yankai Lin, Shuhuai Ren, Peng Li, Jie zhou, Xu sun
Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models.
no code implementations • Findings (ACL) 2021 • Feilong Chen, Xiuyi Chen, Fandong Meng, Peng Li, Jie zhou
Specifically, GoG consists of three sequential graphs: 1) H-Graph, which aims to capture coreference relations among dialog history; 2) History-aware Q-Graph, which aims to fully understand the question through capturing dependency relations between words based on coreference resolution on the dialog history; and 3) Question-aware I-Graph, which aims to capture the relations between objects in an image based on fully question representation.
1 code implementation • Findings (ACL) 2021 • Feilong Chen, Fandong Meng, Xiuyi Chen, Peng Li, Jie zhou
Visual dialogue is a challenging task since it needs to answer a series of coherent questions on the basis of understanding the visual environment.
no code implementations • 16 Sep 2021 • Lei Shen, Jinchao Zhang, Jiao Ou, Xiaofang Zhao, Jie zhou
To address the above issues, we propose a dual-generative model, Dual-Emp, to simultaneously construct the emotion consensus and utilize some external unpaired data.
no code implementations • 14 Sep 2021 • Xueyao Zhang, Jinchao Zhang, Yao Qiu, Li Wang, Jie zhou
Besides, when chords evolve into chord progression, the texture and the form can be bridged by the harmony naturally, which contributes to the joint learning of the two structures.
no code implementations • EMNLP 2021 • Yao Qiu, Jinchao Zhang, Jie zhou
Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing.
1 code implementation • Findings (ACL) 2021 • Yao Qiu, Jinchao Zhang, Jie zhou
(2) RAR forces the model to reconstruct the original sample from its adversarial representation.
no code implementations • 14 Sep 2021 • Yao Qiu, Jinchao Zhang, Huiying Ren, Jie zhou
In this way, our negative instances are fluent, context-related, and more challenging for the model to learn, while can not be positive.
no code implementations • Findings (EMNLP) 2021 • Mingliang Zhang, Fandong Meng, Yunhai Tong, Jie zhou
Therefore, we focus on balancing the learning competencies of different languages and propose Competence-based Curriculum Learning for Multilingual Machine Translation, named CCL-M.
no code implementations • 6 Sep 2021 • Wanhua Li, Jiwen Lu, Abudukelimu Wuerkaixi, Jianjiang Feng, Jie zhou
To address this, we propose a Star-shaped Reasoning Graph Network (S-RGN).
1 code implementation • Findings (EMNLP) 2021 • Duo Zheng, Zipeng Xu, Fandong Meng, Xiaojie Wang, Jiaan Wang, Jie zhou
To enhance VD Questioner: 1) we propose a Related entity enhanced Questioner (ReeQ) that generates questions under the guidance of related entities and learns entity-based questioning strategy from human dialogs; 2) we propose an Augmented Guesser (AugG) that is strong and is optimized for the VD setting especially.
1 code implementation • 4 Sep 2021 • Zhengcong Fei, Zekang Li, Jinchao Zhang, Yang Feng, Jie zhou
Compared to previous dialogue tasks, MOD is much more challenging since it requires the model to understand the multimodal elements as well as the emotions behind them.
1 code implementation • EMNLP 2021 • Yunlong Liang, Chulun Zhou, Fandong Meng, Jinan Xu, Yufeng Chen, Jinsong Su, Jie zhou
Neural Chat Translation (NCT) aims to translate conversational text between speakers of different languages.
1 code implementation • ICCV 2021 • Yi Wei, Shaohui Liu, Yongming Rao, Wang Zhao, Jiwen Lu, Jie zhou
In this work, we present a new multi-view depth estimation method that utilizes both conventional reconstruction and learning-based priors over the recently proposed neural radiance fields (NeRF).
1 code implementation • EMNLP 2021 • Shuhuai Ren, Jinchao Zhang, Lei LI, Xu sun, Jie zhou
Data augmentation aims to enrich training samples for alleviating the overfitting issue in low-resource or class-imbalanced situations.
1 code implementation • EMNLP 2021 • Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jie zhou
Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus bridging the gap between training and inference.
1 code implementation • ICCV 2021 • Wenzhao Zheng, Borui Zhang, Jiwen Lu, Jie zhou
This paper presents a deep relational metric learning (DRML) framework for image clustering and retrieval.
1 code implementation • ICCV 2021 • Yongming Rao, Guangyi Chen, Jiwen Lu, Jie zhou
Unlike most existing methods that learn visual attention based on conventional likelihood, we propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process.
Ranked #4 on
Fine-Grained Image Classification
on FGVC Aircraft
1 code implementation • ICCV 2021 • Xumin Yu, Yongming Rao, Ziyi Wang, Zuyan Liu, Jiwen Lu, Jie zhou
In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr that adopts a transformer encoder-decoder architecture for point cloud completion.
Ranked #1 on
Point Cloud Completion
on ShapeNet
1 code implementation • ICCV 2021 • Xumin Yu, Yongming Rao, Wenliang Zhao, Jiwen Lu, Jie zhou
Assessing action quality is challenging due to the subtle differences between videos and large variations in scores.
Ranked #1 on
Action Quality Assessment
on MTL-AQA
2 code implementations • ICCV 2021 • Yongming Rao, Benlin Liu, Yi Wei, Jiwen Lu, Cho-Jui Hsieh, Jie zhou
In particular, we propose to generate random layouts of a scene by making use of the objects in the synthetic CAD dataset and learn the 3D scene representation by applying object-level contrastive learning on two random scenes generated from the same set of synthetic objects.
no code implementations • 16 Aug 2021 • Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Jia Guo, Jiwen Lu, Dalong Du, Jie zhou
There are second phase of the challenge till October 1, 2021 and on-going leaderboard.
1 code implementation • ICCV 2021 • Wenliang Zhao, Yongming Rao, Ziyi Wang, Jiwen Lu, Jie zhou
Our method is model-agnostic, which can be applied to off-the-shelf backbone networks and metric learning methods.
Ranked #12 on
Metric Learning
on CUB-200-2011
1 code implementation • 12 Aug 2021 • Jiarui Fang, Yang Yu, Zilin Zhu, Shenggui Li, Yang You, Jie zhou
Therefore, we proposed a system called PatrickStar to lower the hardware requirements of PTMs and make them accessible to everyone.
1 code implementation • 11 Aug 2021 • Guangyi Chen, Tianpei Gu, Jiwen Lu, Jin-An Bao, Jie zhou
Experimental results demonstrate the superiority of our method, which outperforms the state-of-the-art methods by a large margin with limited computational cost.
Ranked #13 on
Person Re-Identification
on MSMT17
1 code implementation • ICCV 2021 • Ziwei Wang, Han Xiao, Jiwen Lu, Jie zhou
On the contrary, our GMPQ searches the mixed-quantization policy that can be generalized to largescale datasets with only a small amount of data, so that the search cost is significantly reduced without performance degradation.
no code implementations • WMT (EMNLP) 2021 • Xianfeng Zeng, Yijin Liu, Ernan Li, Qiu Ran, Fandong Meng, Peng Li, Jinan Xu, Jie zhou
This paper introduces WeChat AI's participation in WMT 2021 shared news translation task on English->Chinese, English->Japanese, Japanese->English and English->German.
1 code implementation • 5 Aug 2021 • Zhongjin Luo, Jie zhou, Heming Zhu, Dong Du, Xiaoguang Han, Hongbo Fu
In this work, we propose SimpModeling, a novel sketch-based system for helping users, especially amateur users, easily model 3D animalmorphic heads - a prevalent kind of heads in character design.
1 code implementation • ICCV 2021 • Ziwei Wang, Yunsong Wang, Ziyi Wu, Jiwen Lu, Jie zhou
In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation.
1 code implementation • ACL 2021 • Wenkai Yang, Yankai Lin, Peng Li, Jie zhou, Xu sun
In this work, we point out a potential problem of current backdoor attacking research: its evaluation ignores the stealthiness of backdoor attacks, and most of existing backdoor attacking methods are not stealthy either to system deployers or to system users.
1 code implementation • ICCV 2021 • Guangyi Chen, Junlong Li, Jiwen Lu, Jie zhou
Most existing methods learn to predict future trajectories by behavior clues from history trajectories and interaction clues from environments.
1 code implementation • ACL 2021 • Yunlong Liang, Fandong Meng, Yufeng Chen, Jinan Xu, Jie zhou
Despite the impressive performance of sentence-level and context-aware Neural Machine Translation (NMT), there still remain challenges to translate bilingual conversational text due to its inherent characteristics such as role preference, dialogue coherence, and translation consistency.
1 code implementation • Findings (ACL) 2021 • Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jie zhou
In this way, the model is exactly exposed to predicted tokens for high-confidence positions and still ground-truth tokens for low-confidence positions.
1 code implementation • Findings (ACL) 2021 • Ying Zhang, Fandong Meng, Yufeng Chen, Jinan Xu, Jie zhou
In this paper, we tackle the problem by transferring knowledge from three aspects, i. e., domain, language and task, and strengthening connections among them.
1 code implementation • 12 Jul 2021 • Zipeng Xu, Fandong Meng, Xiaojie Wang, Duo Zheng, Chenxu Lv, Jie zhou
In Reinforcement Learning, it is crucial to represent states and assign rewards based on the action-caused transitions of states.
1 code implementation • 4 Jul 2021 • Linqing Zhao, Jiwen Lu, Jie zhou
To address this, we employ a late fusion strategy where we first learn the geometric and contextual similarities between the input and back-projected (from 2D pixels) point clouds and utilize them to guide the fusion of two modalities to further exploit complementary information.
Ranked #10 on
Semantic Segmentation
on ScanNet
3 code implementations • NeurIPS 2021 • Yongming Rao, Wenliang Zhao, Zheng Zhu, Jiwen Lu, Jie zhou
Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision have shown great potential in achieving promising performance with fewer inductive biases.
Ranked #8 on
Image Classification
on Stanford Cars
(using extra training data)
no code implementations • 29 Jun 2021 • Jianhao Yan, Chenming Wu, Fandong Meng, Jie zhou
However, this evaluation framework suffers from high search errors brought by heuristic search algorithms and is limited by its nature of evaluation over one best candidate.
1 code implementation • CVPR 2021 • Wenzhao Zheng, Chengkun Wang, Jiwen Lu, Jie zhou
In this paper, we propose a deep compositional metric learning (DCML) framework for effective and generalizable similarity measurement between images.
1 code implementation • CVPR 2021 • Shuai Shen, Wanhua Li, Zheng Zhu, Guan Huang, Dalong Du, Jiwen Lu, Jie zhou
To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method.
no code implementations • CVPR 2021 • Guoli Wang, Jiaqi Ma, Qian Zhang, Jiwen Lu, Jie zhou
Many of them settle it by generating fake frontal faces from extreme ones, whereas they are tough to maintain the identity information with high computational consumption and uncontrolled disturbances.
1 code implementation • CVPR 2021 • Shuyan Li, Xiu Li, Jiwen Lu, Jie zhou
Most existing unsupervised video hashing methods are built on unidirectional models with less reliable training objectives, which underuse the correlations among frames and the similarity structure between videos.
1 code implementation • CL (ACL) 2021 • Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng, Jie zhou
Non-Autoregressive Neural Machine Translation (NAT) removes the autoregressive mechanism and achieves significant decoding speedup through generating target words independently and simultaneously.
no code implementations • 15 Jun 2021 • Ganqu Cui, Yufeng Du, Cheng Yang, Jie zhou, Liang Xu, LiFeng Wang, Zhiyuan Liu
The recent emergence of contrastive learning approaches facilitates the research on graph representation learning (GRL), introducing graph contrastive learning (GCL) into the literature.
1 code implementation • ACL 2021 • Yuanxin Liu, Fandong Meng, Zheng Lin, Weiping Wang, Jie zhou
In this paper, however, we observe that although distilling the teacher's hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled.
no code implementations • ACL 2021 • Lei Shen, Fandong Meng, Jinchao Zhang, Yang Feng, Jie zhou
Generating some appealing questions in open-domain conversations is an effective way to improve human-machine interactions and lead the topic to a broader or deeper direction.
1 code implementation • Findings (ACL) 2021 • Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, Jie zhou
Employing human judges to interact with chatbots on purpose to check their capacities is costly and low-efficient, and difficult to get rid of subjective bias.
1 code implementation • ACL 2021 • Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, Jie zhou
Nowadays, open-domain dialogue models can generate acceptable responses according to the historical context based on the large-scale pre-trained language models.
1 code implementation • NeurIPS 2021 • Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie zhou, Cho-Jui Hsieh
Based on this observation, we propose a dynamic token sparsification framework to prune redundant tokens progressively and dynamically based on the input.
Ranked #181 on
Image Classification
on ImageNet
1 code implementation • ACL 2021 • Hui Jiang, Chulun Zhou, Fandong Meng, Biao Zhang, Jie zhou, Degen Huang, Qingqiang Wu, Jinsong Su
Due to the great potential in facilitating software development, code generation has attracted increasing attention recently.
no code implementations • NAACL 2021 • Yingxue Zhang, Fandong Meng, Peng Li, Ping Jian, Jie zhou
Implicit discourse relation recognition (IDRR) aims to identify logical relations between two adjacent sentences in the discourse.
1 code implementation • ACL 2022 • Weize Chen, Xu Han, Yankai Lin, Hexu Zhao, Zhiyuan Liu, Peng Li, Maosong Sun, Jie zhou
Hyperbolic neural networks have shown great potential for modeling complex data.
1 code implementation • ACL 2021 • Ziqi Wang, Xiaozhi Wang, Xu Han, Yankai Lin, Lei Hou, Zhiyuan Liu, Peng Li, Juanzi Li, Jie zhou
Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning.
2 code implementations • 28 May 2021 • Yujia Qin, Yankai Lin, Jing Yi, Jiajie Zhang, Xu Han, Zhengyan Zhang, Yusheng Su, Zhiyuan Liu, Peng Li, Maosong Sun, Jie zhou
Specifically, we introduce a pre-training framework named "knowledge inheritance" (KI) and explore how could knowledge distillation serve as auxiliary supervision during pre-training to efficiently learn larger PLMs.
1 code implementation • ACL 2021 • Fusheng Wang, Jianhao Yan, Fandong Meng, Jie zhou
As an active research field in NMT, knowledge distillation is widely applied to enhance the model's performance by transferring teacher model's knowledge on each training sample.
1 code implementation • ACL 2021 • Yangyifan Xu, Yijin Liu, Fandong Meng, Jiajun Zhang, Jinan Xu, Jie zhou
Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training weights to different tokens, in order to alleviate the token imbalance problem.
1 code implementation • ACL 2021 • Mengqi Miao, Fandong Meng, Yijin Liu, Xiao-Hua Zhou, Jie zhou
The Neural Machine Translation (NMT) model is essentially a joint language model conditioned on both the source sentence and partial translation.
1 code implementation • Findings (ACL) 2021 • Tianyu Gao, Xu Han, Keyue Qiu, Yuzhuo Bai, Zhiyu Xie, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie zhou
Distantly supervised (DS) relation extraction (RE) has attracted much attention in the past few years as it can utilize large-scale auto-labeled data.
1 code implementation • 17 May 2021 • Yi Wei, Shang Su, Jiwen Lu, Jie zhou
To tackle this problem, we propose frustum-aware geometric reasoning (FGR) to detect vehicles in point clouds without any 3D annotations.
no code implementations • 6 May 2021 • Jingyu Guo, Wei Wang, Wenming Yang, Qingmin Liao, Jie zhou
In this paper, we introduce a brand new scheme, namely external-reference image quality assessment (ER-IQA), by introducing external reference images to bridge the gap between FR and NR-IQA.
no code implementations • 6 Apr 2021 • Jiabin Zhang, Zheng Zhu, Jiwen Lu, JunJie Huang, Guan Huang, Jie zhou
To make a better trade-off between accuracy and efficiency, we propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE).
2 code implementations • CVPR 2021 • Yunpeng Zhang, Jiwen Lu, Jie zhou
The precise localization of 3D objects from a single image without depth information is a highly challenging problem.
Ranked #3 on
Monocular 3D Object Detection
on KITTI Cars Moderate
no code implementations • EACL 2021 • Jie zhou, Yuanbin Wu, Changzhi Sun, Liang He
Modelling a word{'}s polarity in different contexts is a key task in sentiment analysis.
no code implementations • CVPR 2021 • Wanhua Li, Shiwei Wang, Jiwen Lu, Jianjiang Feng, Jie zhou
In the end, the samples in the unbalanced train batch are re-weighted by the learned meta-miner to optimize the kinship models.
1 code implementation • CVPR 2021 • Wanhua Li, Xiaoke Huang, Jiwen Lu, Jianjiang Feng, Jie zhou
An ordinal distribution constraint is proposed to exploit the ordinal nature of regression.
no code implementations • 24 Mar 2021 • Shuai Shen, Wanhua Li, Zheng Zhu, Guan Huang, Dalong Du, Jiwen Lu, Jie zhou
To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method.
no code implementations • CVPR 2021 • Zheng Zhu, Guan Huang, Jiankang Deng, Yun Ye, JunJie Huang, Xinze Chen, Jiagang Zhu, Tian Yang, Jiwen Lu, Dalong Du, Jie zhou
In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol.
Ranked #1 on
Face Verification
on IJB-C
(dataset metric)
no code implementations • 19 Feb 2021 • Xiyun Zhang, Zhongyuan Ruan, Muhua Zheng, Jie zhou, Stefano Boccaletti, Baruch Barzel
Specifically, we detect a new pandemic phase - the mutated phase - in which, despite the fact that the pathogen is initially non-pandemic (R0 < 1), it may still spread due to the emergence of a critical mutation.
1 code implementation • 18 Feb 2021 • Wencheng Zhu, Jiahao Li, Jiwen Lu, Jie zhou
Specifically, we first compute a pixel-wise similarity matrix by using representations of reference and target pixels and then select top-rank reference pixels for target pixel classification.
One-shot visual object segmentation
Video Semantic Segmentation
1 code implementation • 7 Feb 2021 • Yusheng Su, Xu Han, Yankai Lin, Zhengyan Zhang, Zhiyuan Liu, Peng Li, Jie zhou, Maosong Sun
We then perform contrastive semi-supervised learning on both the retrieved unlabeled and original labeled instances to help PLMs capture crucial task-related semantic features.
no code implementations • 4 Feb 2021 • Ke Chen, Xiaojing Bai, Xulin Mu, Pengfei Yan, Nianxiang Qiu, Youbing Li, Jie zhou, Yujie Song, Yiming Zhang, Shiyu Du, Zhifang Chai, Qing Huang
The elemental diversity is crucial to screen out ternary MAX phases with outstanding properties via tuning of bonding types and strength between constitutive atoms.
Materials Science
no code implementations • 2 Feb 2021 • Cheng Ma, Jiwen Lu, Jie zhou
As hashing becomes an increasingly appealing technique for large-scale image retrieval, multi-label hashing is also attracting more attention for the ability to exploit multi-level semantic contents.
no code implementations • 30 Jan 2021 • Mingliang Xiong, Mingqing Liu, Qingwei Jiang, Jie zhou, Qingwen Liu, Hao Deng
Optical wireless communications (OWC) utilizing infrared or visible light as the carrier attracts great attention in 6G research.
no code implementations • 20 Jan 2021 • Zekang Li, Zongjia Li, Jinchao Zhang, Yang Feng, Jie zhou
We participate in the DSTC9 Interactive Dialogue Evaluation Track (Gunasekara et al. 2020) sub-task 1 (Knowledge Grounded Dialogue) and sub-task 2 (Interactive Dialogue).
no code implementations • 19 Jan 2021 • Lei He, Jiwen Lu, Guanghui Wang, Shiyu Song, Jie zhou
In this paper, we first introduce the concept of semantic objectness to exploit the geometric relationship of these two tasks through an analysis of the imaging process, then propose a Semantic Object Segmentation and Depth Estimation Network (SOSD-Net) based on the objectness assumption.
Ranked #39 on
Semantic Segmentation
on NYU Depth v2
no code implementations • 7 Jan 2021 • Jingyu Gong, Jiachen Xu, Xin Tan, Jie zhou, Yanyun Qu, Yuan Xie, Lizhuang Ma
Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in feature extraction, leading to misclassification in the transition area between two objects.
no code implementations • 4 Jan 2021 • Xiaoyang Zheng, Xin Tan, Jie zhou, Lizhuang Ma, Rynson W. H. Lau
This allows the supervision to be aligned with the property of saliency detection, where the salient objects of an image could be from more than one class.
no code implementations • ICCV 2021 • Bingyao Yu, Wanhua Li, Xiu Li, Jiwen Lu, Jie zhou
In this paper, we propose a frequency-aware spatiotemporal transformers for deep In this paper, we propose a Frequency-Aware Spatiotemporal Transformer (FAST) for video inpainting detection, which aims to simultaneously mine the traces of video inpainting from spatial, temporal, and frequency domains.
1 code implementation • ACL 2021 • Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun, Jie zhou
Pre-trained Language Models (PLMs) have shown superior performance on various downstream Natural Language Processing (NLP) tasks.
1 code implementation • Findings (EMNLP) 2021 • Lei LI, Yankai Lin, Deli Chen, Shuhuai Ren, Peng Li, Jie zhou, Xu sun
On the other hand, the exiting decisions made by internal classifiers are unreliable, leading to wrongly emitted early predictions.
2 code implementations • 18 Dec 2020 • An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie zhou
Most existing point cloud instance and semantic segmentation methods rely heavily on strong supervision signals, which require point-level labels for every point in the scene.
no code implementations • 14 Dec 2020 • Deli Chen, Yankai Lin, Lei LI, Xuancheng Ren, Peng Li, Jie zhou, Xu sun
Graph Contrastive Learning (GCL) has proven highly effective in promoting the performance of Semi-Supervised Node Classification (SSNC).
1 code implementation • 9 Dec 2020 • Yunlong Liang, Fandong Meng, Ying Zhang, Jinan Xu, Yufeng Chen, Jie zhou
Firstly, we design a Heterogeneous Graph-Based Encoder to represent the conversation content (i. e., the dialogue history, its emotion flow, facial expressions, audio, and speakers' personalities) with a heterogeneous graph neural network, and then predict suitable emotions for feedback.