1 code implementation • 30 Apr 2024 • Zhanwei Zhang, Zishuo Hua, Minghao Chen, Wei Lu, Binbin Lin, Deng Cai, Wenxiao Wang
Finally, to ensure the optimal granularity of key steps, we design a selectable granularity strategy that caters to each predicted trajectory.
no code implementations • 30 Apr 2024 • Zhanwei Zhang, Minghao Chen, Shuai Xiao, Liang Peng, Hengjia Li, Binbin Lin, Ping Li, Wenxiao Wang, Boxi Wu, Deng Cai
Specifically, in the selection process, to improve the reliability of pseudo boxes, we propose a complementary augmentation strategy.
no code implementations • 24 Apr 2024 • Jincheng Dai, Zhuowei Huang, Haiyun Jiang, Chen Chen, Deng Cai, Wei Bi, Shuming Shi
Large Language Models (LLMs), despite their impressive performance on a wide range of tasks, require significant GPU memory and consume substantial computational resources.
1 code implementation • 25 Mar 2024 • Huayang Li, Deng Cai, Zhi Qu, Qu Cui, Hidetaka Kamigaito, Lemao Liu, Taro Watanabe
In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information.
1 code implementation • 18 Mar 2024 • Yang Yang, Wen Wang, Liang Peng, Chaotian Song, Yao Chen, Hengjia Li, Xiaolong Yang, Qinglin Lu, Deng Cai, Boxi Wu, Wei Liu
Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts.
no code implementations • 8 Mar 2024 • Shuaiyi Li, Yang Deng, Deng Cai, Hongyuan Lu, Liang Chen, Wai Lam
As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing in order to seek an effective, consecutive, and batch-supportive way to edit the model behavior directly.
no code implementations • 27 Feb 2024 • Bowen Cao, Deng Cai, Leyang Cui, Xuxin Cheng, Wei Bi, Yuexian Zou, Shuming Shi
To address this, we propose to initialize the training oracles using linguistic heuristics and, more importantly, bootstrap the oracles through iterative self-reinforcement.
1 code implementation • 22 Feb 2024 • Chenxi Huang, Yuenan Hou, Weicai Ye, Di Huang, Xiaoshui Huang, Binbin Lin, Deng Cai, Wanli Ouyang
We project the freely available 3D segmentation annotations onto the 2D plane and leverage the corresponding 2D semantic maps as the supervision signal, significantly enhancing the semantic awareness of multi-view detectors.
no code implementations • 15 Feb 2024 • Wenxiao Wang, Wei Chen, Yicong Luo, Yongliu Long, Zhengkai Lin, Liye Zhang, Binbin Lin, Deng Cai, Xiaofei He
However, Large language models have two prominent characteristics compared to smaller models: (1) Most of compression algorithms require finetuning or even retraining the model after compression.
no code implementations • 10 Feb 2024 • Chufan Shi, Deng Cai, Yujiu Yang
In the rapidly evolving field of text generation, the demand for more precise control mechanisms has become increasingly apparent.
no code implementations • 10 Feb 2024 • Chufan Shi, Haoran Yang, Deng Cai, Zhisong Zhang, Yifan Wang, Yujiu Yang, Wai Lam
Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers.
no code implementations • 23 Jan 2024 • Hengjia Li, Yang Liu, Yuqi Lin, Zhanwei Zhang, Yibo Zhao, weihang Pan, Tu Zheng, Zheng Yang, Yuchun Jiang, Boxi Wu, Deng Cai
In this paper, we propose UniHDA, a \textbf{unified} and \textbf{versatile} framework for generative hybrid domain adaptation with multi-modal references from multiple domains.
1 code implementation • 19 Jan 2024 • Fanqi Wan, Xinting Huang, Deng Cai, Xiaojun Quan, Wei Bi, Shuming Shi
In this paper, we introduce the notion of knowledge fusion for LLMs, aimed at combining the capabilities of existing LLMs and transferring them into a single LLM.
1 code implementation • 16 Jan 2024 • Shuming Shi, Enbo Zhao, Deng Cai, Leyang Cui, Xinting Huang, Huayang Li
We present Inferflow, an efficient and highly configurable inference engine for large language models (LLMs).
1 code implementation • 22 Dec 2023 • Weiwen Xu, Deng Cai, Zhisong Zhang, Wai Lam, Shuming Shi
As humans, we consistently engage in interactions with our peers and receive feedback in the form of natural language.
1 code implementation • 20 Dec 2023 • Yuqi Lin, Minghao Chen, Kaipeng Zhang, Hengjia Li, Mingming Li, Zheng Yang, Dongqin Lv, Binbin Lin, Haifeng Liu, Deng Cai
As a result, we dissect the preservation of patch-wise spatial information in CLIP and proposed a local-to-global framework to obtain image tags.
1 code implementation • 19 Dec 2023 • Junkai Xu, Liang Peng, Haoran Cheng, Linxuan Xia, Qi Zhou, Dan Deng, Wei Qian, Wenxiao Wang, Deng Cai
To resolve this problem, we propose to regulate intermediate dense 3D features with the help of volume rendering.
no code implementations • 25 Nov 2023 • Zhanyu Wang, Longyue Wang, Zhen Zhao, Minghao Wu, Chenyang Lyu, Huayang Li, Deng Cai, Luping Zhou, Shuming Shi, Zhaopeng Tu
While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of input-side multimodal comprehension, lacking the capacity for multimodal content generation.
no code implementations • 16 Nov 2023 • Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong
Text watermarking has emerged as an important technique for detecting machine-generated text.
no code implementations • 15 Nov 2023 • Chang Gao, Haiyun Jiang, Deng Cai, Shuming Shi, Wai Lam
Most existing chain-of-thought (CoT) prompting methods suffer from the issues of generalizability and consistency, as they often rely on instance-specific solutions that may not be applicable to other cases and lack task-level consistency in their reasoning steps.
no code implementations • 23 Oct 2023 • Chufan Shi, Yixuan Su, Cheng Yang, Yujiu Yang, Deng Cai
Although instruction tuning has proven to be a data-efficient method for transforming LLMs into such generalist models, their performance still lags behind specialist models trained exclusively for specific tasks.
1 code implementation • 14 Sep 2023 • Huayang Li, Siheng Li, Deng Cai, Longyue Wang, Lemao Liu, Taro Watanabe, Yujiu Yang, Shuming Shi
We release our dataset, model, and demo to foster future research in the area of multimodal instruction following.
Ranked #93 on Visual Question Answering on MM-Vet
1 code implementation • 3 Sep 2023 • Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, Longyue Wang, Anh Tuan Luu, Wei Bi, Freda Shi, Shuming Shi
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge.
1 code implementation • ICCV 2023 • Junkai Xu, Liang Peng, Haoran Cheng, Hao Li, Wei Qian, Ke Li, Wenxiao Wang, Deng Cai
To the best of our knowledge, this work is the first to introduce volume rendering for M3D, and demonstrates the potential of implicit reconstruction for image-based 3D perception.
1 code implementation • 16 Aug 2023 • Yangyi Huang, Hongwei Yi, Yuliang Xiu, Tingting Liao, Jiaxiang Tang, Deng Cai, Justus Thies
But how to effectively capture all visual attributes of an individual from a single image, which are sufficient to reconstruct unseen areas (e. g., the back view)?
1 code implementation • 1 Aug 2023 • Zhihao Chi, Tu Zheng, Hengjia Li, Zheng Yang, Boxi Wu, Binbin Lin, Deng Cai
In this paper, we restudy the hyper-parameter temperature and figure out its incapability to distill the knowledge from each sample sufficiently when it is a single value.
no code implementations • 16 Jul 2023 • Longyue Wang, Zefeng Du, Donghuai Liu, Deng Cai, Dian Yu, Haiyun Jiang, Yan Wang, Leyang Cui, Shuming Shi, Zhaopeng Tu
Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP).
1 code implementation • 13 Jul 2023 • Tian Lan, Deng Cai, Yan Wang, Heyan Huang, Xian-Ling Mao
The dominant text generation models compose the output by sequentially selecting words from a fixed vocabulary.
1 code implementation • 25 May 2023 • Liang Peng, Junkai Xu, Haoran Cheng, Zheng Yang, Xiaopei Wu, Wei Qian, Wenxiao Wang, Boxi Wu, Deng Cai
Monocular 3D detection is a challenging task due to the lack of accurate 3D information.
1 code implementation • 25 May 2023 • Yixuan Su, Tian Lan, Huayang Li, Jialu Xu, Yan Wang, Deng Cai
To do so, PandaGPT combines the multimodal encoders from ImageBind and the large language models from Vicuna.
1 code implementation • 22 May 2023 • Haoran Yang, Deng Cai, Huayang Li, Wei Bi, Wai Lam, Shuming Shi
We introduce a frustratingly simple, super efficient and surprisingly effective decoding method, which we call Frustratingly Simple Decoding (FSD), for neural text generation.
no code implementations • 22 May 2023 • Yue Zhang, Leyang Cui, Deng Cai, Xinting Huang, Tao Fang, Wei Bi
Proprietary Large Language Models (LLMs), such as ChatGPT, have garnered significant attention due to their exceptional capabilities in handling a diverse range of tasks.
no code implementations • 18 Apr 2023 • Yang Liu, Shen Yan, Yuge Zhang, Kan Ren, Quanlu Zhang, Zebin Ren, Deng Cai, Mi Zhang
Vision Transformers have shown great performance in single tasks such as classification and segmentation.
no code implementations • 31 Mar 2023 • Hengjia Li, Tu Zheng, Zhihao Chi, Zheng Yang, Wenxiao Wang, Boxi Wu, Binbin Lin, Deng Cai
To tackle these problems, we propose Asymmetric Parallel Point Transformer (APPT).
no code implementations • 27 Mar 2023 • Chenxi Huang, Liang Xie, Yibo Yang, Wenxiao Wang, Binbin Lin, Deng Cai
One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant differences in local updates and affect the performance of the central server.
no code implementations • 20 Feb 2023 • Liang Xie, Yibo Yang, Wenxiao Wang, Binbin Lin, Deng Cai, Xiaofei He, Ronghua Liang
Compared to 2D images, 3D point clouds are much more sensitive to rotations.
no code implementations • 7 Feb 2023 • Xiaohu Tang, Yang Wang, Ting Cao, Li Lyna Zhang, Qi Chen, Deng Cai, Yunxin Liu, Mao Yang
On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts.
1 code implementation • 20 Dec 2022 • Chenxi Huang, Tong He, Haidong Ren, Wenxiao Wang, Binbin Lin, Deng Cai
Unfortunately, the network cannot accurately distinguish different depths from such non-discriminative visual features, resulting in unstable depth training.
no code implementations • 6 Dec 2022 • Minghao Chen, Renbo Tu, Chenxi Huang, Yuqi Lin, Boxi Wu, Deng Cai
In this paper, we introduce a new framework of contrastive action representation learning (CARL) to learn frame-wise action representation in a self-supervised or weakly-supervised manner, especially for long videos.
no code implementations • ICCV 2023 • Yangyi Huang, Hongwei Yi, Weiyang Liu, Haofan Wang, Boxi Wu, Wenxiao Wang, Binbin Lin, Debing Zhang, Deng Cai
Most of these methods fail to achieve realistic reconstruction when only a single image is available.
no code implementations • 14 Nov 2022 • Xiaopei Wu, Yang Zhao, Liang Peng, Hua Chen, Xiaoshui Huang, Binbin Lin, Haifeng Liu, Deng Cai, Wanli Ouyang
When training a teacher-student semi-supervised framework, we randomly select gt samples and pseudo samples to both labeled frames and unlabeled frames, making a strong data augmentation for them.
1 code implementation • 13 Nov 2022 • Nuo Chen, Yan Wang, Haiyun Jiang, Deng Cai, Yuhan Li, Ziyang Chen, Longyue Wang, Jia Li
In this paper, we introduce the Harry Potter Dialogue (HPD) dataset, designed to advance the study of dialogue agents and character alignment.
1 code implementation • 26 Oct 2022 • Huayang Li, Deng Cai, Jin Xu, Taro Watanabe
The combination of $n$-gram and neural LMs not only allows the neural part to focus on the deeper understanding of language but also provides a flexible way to customize an LM by switching the underlying $n$-gram model without changing the neural model.
1 code implementation • 18 Oct 2022 • Deng Cai, Xin Li, Jackie Chun-Sing Ho, Lidong Bing, Wai Lam
Unlike most prior work that only evaluates the ability to measure semantic similarity, we present a thorough evaluation of existing multilingual sentence embeddings and our improved versions, which include a collection of five transfer tasks in different downstream applications.
no code implementations • 29 Aug 2022 • Boxi Wu, Jie Jiang, Haidong Ren, Zifan Du, Wenxiao Wang, Zhifeng Li, Deng Cai, Xiaofei He, Binbin Lin, Wei Liu
Various training criteria for these auxiliary outliers are proposed based on heuristic intuitions.
1 code implementation • 7 Aug 2022 • Honghui Yang, Zili Liu, Xiaopei Wu, Wenxiao Wang, Wei Qian, Xiaofei He, Deng Cai
The dynamic farthest voxel sampling is then applied to evenly sample the points.
no code implementations • 21 Jul 2022 • Boxi Wu, Jindong Gu, Zhifeng Li, Deng Cai, Xiaofei He, Wei Liu
Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network (CNN), has received much attention.
1 code implementation • 18 Jul 2022 • Liang Peng, Xiaopei Wu, Zheng Yang, Haifeng Liu, Deng Cai
Therefore, we propose to reformulate the instance depth to the combination of the instance visual surface depth (visual depth) and the instance attribute depth (attribute depth).
1 code implementation • 16 Jun 2022 • Ziqian Dai, Jianwei Yu, Yan Wang, Nuo Chen, Yanyao Bian, Guangzhi Li, Deng Cai, Dong Yu
Prosodic boundary plays an important role in text-to-speech synthesis (TTS) in terms of naturalness and readability.
2 code implementations • 6 Jun 2022 • Jin Xu, Xiaojiang Liu, Jianhao Yan, Deng Cai, Huayang Li, Jian Li
While large-scale neural language models, such as GPT2 and BART, have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decoding algorithms (\textit{e. g.}, greedy search).
no code implementations • 19 Apr 2022 • Liang Xie, Yibo Yang, Deng Cai, Xiaofei He
Class imbalance distribution widely exists in real-world engineering.
1 code implementation • CVPR 2022 • Minghao Chen, Fangyun Wei, Chong Li, Deng Cai
In this paper, we introduce a novel contrastive action representation learning (CARL) framework to learn frame-wise action representations, especially for long videos, in a self-supervised manner.
no code implementations • 23 Mar 2022 • Yizhe Zhang, Deng Cai
We demonstrate that MemSizer provides an improved balance between efficiency and accuracy over the vanilla transformer and other efficient transformer variants in three typical sequence generation tasks, including machine translation, abstractive text summarization, and language modeling.
3 code implementations • CVPR 2022 • Tu Zheng, Yifei HUANG, Yang Liu, Wenjian Tang, Zheng Yang, Deng Cai, Xiaofei He
In this way, we can exploit more contextual information to detect lanes while leveraging local detailed lane features to improve localization accuracy.
Ranked #1 on Lane Detection on LLAMAS
1 code implementation • CVPR 2022 • Xiaopei Wu, Liang Peng, Honghui Yang, Liang Xie, Chenxi Huang, Chengqi Deng, Haifeng Liu, Deng Cai
Many multi-modal methods are proposed to alleviate this issue, while different representations of images and point clouds make it difficult to fuse them, resulting in suboptimal performance.
1 code implementation • ICLR 2022 • Liang Peng, Senbo Yan, Boxi Wu, Zheng Yang, Xiaofei He, Deng Cai
This network is learned by minimizing our newly-proposed 3D alignment loss between the 3D box estimates and the corresponding RoI LiDAR points.
no code implementations • 7 Feb 2022 • Deng Cai, Elman Mansimov, Yi-An Lai, Yixuan Su, Lei Shu, Yi Zhang
First, we measure and analyze model update regression in different model update settings.
no code implementations • 2 Feb 2022 • Huayang Li, Yixuan Su, Deng Cai, Yan Wang, Lemao Liu
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community.
no code implementations • 14 Dec 2021 • Yazheng Yang, Boyuan Pan, Deng Cai, Huan Sun
In particular, instead of directly generating a story, we first learn to map the short text input to a low-dimensional topic distribution (which is pre-assigned by a topic model).
1 code implementation • 13 Oct 2021 • Tian Lan, Deng Cai, Yan Wang, Yixuan Su, Heyan Huang, Xian-Ling Mao
In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using a dense retrieval model.
1 code implementation • Findings (EMNLP) 2021 • Deng Cai, Xin Li, Jackie Chun-Sing Ho, Lidong Bing, Wai Lam
We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher.
no code implementations • 29 Sep 2021 • Liang Peng, Senbo Yan, Chenxi Huang, Xiaofei He, Deng Cai
This characteristic indicates that monocular 3D detection is inherently different from other typical detection tasks that have the same dimensional input and output.
2 code implementations • ACL 2022 • Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, Yi Zhang
Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems.
1 code implementation • Findings (EMNLP) 2021 • Weiwen Xu, Yang Deng, Huihui Zhang, Deng Cai, Wai Lam
We propose a novel Chain Guided Retriever-reader ({\tt CGR}) framework to model the reasoning chain for multi-hop Science Question Answering.
no code implementations • 30 Aug 2021 • Lingyun Feng, Jianwei Yu, Deng Cai, Songxiang Liu, Haitao Zheng, Yan Wang
%To facilitate the research on ASR-robust general language understanding, In this paper, we propose ASR-GLUE benchmark, a new collection of 6 different NLU tasks for evaluating the performance of models under ASR error across 3 different levels of background noise and 6 speakers with various voice characteristics.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
3 code implementations • ICLR 2022 • Wenxiao Wang, Lu Yao, Long Chen, Binbin Lin, Deng Cai, Xiaofei He, Wei Liu
On the one hand, CEL blends each embedding with multiple patches of different scales, providing the self-attention module itself with cross-scale features.
Ranked #42 on Semantic Segmentation on ADE20K val
1 code implementation • CVPR 2022 • Yang Liu, Weifeng Zhang, Chao Xiang, Tu Zheng, Deng Cai, Xiaofei He
Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks not seen during training, given only a few examples.
no code implementations • 9 Jun 2021 • Boxi Wu, Heng Pan, Li Shen, Jindong Gu, Shuai Zhao, Zhifeng Li, Deng Cai, Xiaofei He, Wei Liu
In this work, we find that the adversarial attacks can also be vulnerable to small perturbations.
1 code implementation • ICCV 2021 • Hao Fang, Daoxin Zhang, Yi Zhang, Minghao Chen, Jiawei Li, Yao Hu, Deng Cai, Xiaofei He
In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency.
1 code implementation • Findings (ACL) 2021 • Weiwen Xu, Huihui Zhang, Deng Cai, Wai Lam
Our framework contains three new ideas: (a) {\tt AMR-SG}, an AMR-based Semantic Graph, constructed by candidate fact AMRs to uncover any hop relations among question, answer and multiple facts.
1 code implementation • ACL 2021 • Deng Cai, Yan Wang, Huayang Li, Wai Lam, Lemao Liu
Second, the memory retriever and NMT model can be jointly optimized for the ultimate translation goal.
1 code implementation • Findings (ACL) 2021 • Jiannan Xiang, Yahui Liu, Deng Cai, Huayang Li, Defu Lian, Lemao Liu
An important aspect of developing dialogue systems is how to evaluate and compare the performance of different systems.
no code implementations • 29 Apr 2021 • Xin Guo, Zhongming Jin, Chong Chen, Helei Nie, Jianqiang Huang, Deng Cai, Xiaofei He, Xiansheng Hua
In this paper, we propose a DiscRiminative-gEnerative duAl Memory (DREAM) anomaly detection model to take advantage of a few anomalies and solve data imbalance.
1 code implementation • 19 Apr 2021 • Liang Peng, Fei Liu, Zhengxu Yu, Senbo Yan, Dan Deng, Zheng Yang, Haifeng Liu, Deng Cai
We delve into this underlying mechanism and then empirically find that: concerning the label accuracy, the 3D location part in the label is preferred compared to other parts of labels.
no code implementations • 13 Apr 2021 • Liang Peng, Fei Liu, Senbo Yan, Xiaofei He, Deng Cai
Image-only and pseudo-LiDAR representations are commonly used for monocular 3D object detection.
1 code implementation • 1 Apr 2021 • Tu Zheng, Shuai Zhao, Yang Liu, Zili Liu, Deng Cai
In this paper, we propose Side Overlap~(SO) loss by maximizing the side overlap of two bounding boxes, which puts more penalty for low overlapping bounding box cases.
no code implementations • 24 Mar 2021 • Liang Xie, Guodong Xu, Deng Cai, Xiaofei He
3D object detection algorithms for autonomous driving reason about 3D obstacles either from 3D birds-eye view or perspective view or both.
1 code implementation • 18 Mar 2021 • Zili Liu, Guodong Xu, Honghui Yang, Minghao Chen, Kuoliang Wu, Zheng Yang, Haifeng Liu, Deng Cai
In this work, we propose a suppress-and-refine framework to remove these handcrafted components.
no code implementations • 15 Mar 2021 • Yang Liu, Tu Zheng, Jie Song, Deng Cai, Xiaofei He
In this paper, we argue that a Mutual Nearest Neighbor (MNN) relation should be established to explicitly select the query descriptors that are most relevant to each task and discard less relevant ones from aggregative clutters in FSL.
no code implementations • 10 Mar 2021 • Dong Shen, Shuai Zhao, Jinming Hu, Hao Feng, Deng Cai, Xiaofei He
In this paper, we propose a novel network, Erasing-Salient Net (ES-Net), to learn comprehensive features by erasing the salient areas in an image.
1 code implementation • EACL 2021 • Yixuan Su, Deng Cai, Yan Wang, David Vandyke, Simon Baker, Piji Li, Nigel Collier
In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance.
no code implementations • 29 Jan 2021 • Hao Feng, Minghao Chen, Jinming Hu, Dong Shen, Haifeng Liu, Deng Cai
In this paper, to complement these low recall neighbor pseudo labels, we propose a joint learning framework to learn better feature embeddings via high precision neighbor pseudo labels and high recall group pseudo labels.
1 code implementation • ACL 2021 • Yixuan Su, Deng Cai, Qingyu Zhou, Zibo Lin, Simon Baker, Yunbo Cao, Shuming Shi, Nigel Collier, Yan Wang
As for IC, it progressively strengthens the model's ability in identifying the mismatching information between the dialogue context and a response candidate.
Ranked #3 on Conversational Response Selection on RRS
no code implementations • 21 Dec 2020 • Deng Cai, Yizhe Zhang, Yichen Huang, Wai Lam, Bill Dolan
We propose the task of narrative incoherence detection as a new arena for inter-sentential semantic understanding: Given a multi-sentence narrative, decide whether there exist any semantic discrepancies in the narrative flow.
2 code implementations • 30 Nov 2020 • Shuai Zhao, Liguang Zhou, Wenxiao Wang, Deng Cai, Tin Lun Lam, Yangsheng Xu
Each of these small networks has a fraction of the original one's parameters.
Ranked #26 on Image Classification on CIFAR-10
2 code implementations • 18 Nov 2020 • Minghui Qiu, Peng Li, Chengyu Wang, Hanjie Pan, Ang Wang, Cen Chen, Xianyan Jia, Yaliang Li, Jun Huang, Deng Cai, Wei Lin
The literature has witnessed the success of leveraging Pre-trained Language Models (PLMs) and Transfer Learning (TL) algorithms to a wide range of Natural Language Processing (NLP) applications, yet it is not easy to build an easy-to-use and scalable TL toolkit for this purpose.
no code implementations • 21 Oct 2020 • Liang Peng, Dan Deng, Deng Cai
Occlusion handling is a challenging problem in stereo matching, especially for unsupervised methods.
1 code implementation • 15 Oct 2020 • Jia Guo, Minghao Chen, Yao Hu, Chen Zhu, Xiaofei He, Deng Cai
We investigate this problem by study the gap of confidence between teacher and student.
no code implementations • 10 Oct 2020 • Wenxiao Wang, Minghao Chen, Shuai Zhao, Long Chen, Jinming Hu, Haifeng Liu, Deng Cai, Xiaofei He, Wei Liu
Specifically, it first casts the relationships between a certain model's accuracy and depth/width/resolution into a polynomial regression and then maximizes the polynomial to acquire the optimal values for the three dimensions.
1 code implementation • NeurIPS 2021 • Boxi Wu, Jinghui Chen, Deng Cai, Xiaofei He, Quanquan Gu
Previous empirical results suggest that adversarial training requires wider networks for better performances.
3 code implementations • 31 Aug 2020 • Tu Zheng, Hao Fang, Yi Zhang, Wenjian Tang, Zheng Yang, Haifeng Liu, Deng Cai
Lane detection is one of the most important tasks in self-driving.
Ranked #4 on Lane Detection on TuSimple
no code implementations • 14 Aug 2020 • Zelong Yang, Zhufeng Pan, Yan Wang, Deng Cai, Xiaojiang Liu, Shuming Shi, Shao-Lun Huang
With the rapid prevalence and explosive development of MOBA esports (Multiplayer Online Battle Arena electronic sports), much research effort has been devoted to automatically predicting game results (win predictions).
no code implementations • 14 Aug 2020 • Zhengxu Yu, Yilun Zhao, Bin Hong, Zhongming Jin, Jianqiang Huang, Deng Cai, Xiaofei He, Xian-Sheng Hua
Therefore, it is critical to learn an apparel-invariant person representation under cases like cloth changing or several persons wearing similar clothes.
1 code implementation • 12 Aug 2020 • Wenqing Chu, Wei-Chih Hung, Yi-Hsuan Tsai, Yu-Ting Chang, Yijun Li, Deng Cai, Ming-Hsuan Yang
Caricature is an artistic drawing created to abstract or exaggerate facial features of a person.
1 code implementation • 10 Aug 2020 • Yahui Liu, Marco De Nadai, Deng Cai, Huayang Li, Xavier Alameda-Pineda, Nicu Sebe, Bruno Lepri
Our proposed model disentangles the image content from the visual attributes, and it learns to modify the latter using the textual description, before generating a new image from the content and the modified attribute representation.
no code implementations • 30 Jul 2020 • Xin Guo, Zhengxu Yu, Chao Xiang, Zhongming Jin, Jianqiang Huang, Deng Cai, Xiaofei He, Xian-Sheng Hua
Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting.
1 code implementation • ICML 2020 • Boyuan Pan, Yazheng Yang, Kaizhao Liang, Bhavya Kailkhura, Zhongming Jin, Xian-Sheng Hua, Deng Cai, Bo Li
Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation.
3 code implementations • ACL 2020 • Deng Cai, Wai Lam
We propose a new end-to-end model that treats AMR parsing as a series of dual decisions on the input sequence and the incrementally constructed graph.
Ranked #3 on AMR Parsing on LDC2014T12
no code implementations • EMNLP 2020 • Zibo Lin, Deng Cai, Yan Wang, Xiaojiang Liu, Hai-Tao Zheng, Shuming Shi
Despite that response selection is naturally a learning-to-rank problem, most prior works take a point-wise view and train binary classifiers for this task: each response candidate is labeled either relevant (one) or irrelevant (zero).
Ranked #10 on Conversational Response Selection on E-commerce
no code implementations • 5 Apr 2020 • Yixuan Su, Deng Cai, Yan Wang, Simon Baker, Anna Korhonen, Nigel Collier, Xiaojiang Liu
To enable better balance between the content quality and the style, we introduce a new training strategy, know as Information-Guided Reinforcement Learning (IG-RL).
no code implementations • 5 Apr 2020 • Yixuan Su, Yan Wang, Simon Baker, Deng Cai, Xiaojiang Liu, Anna Korhonen, Nigel Collier
A stylistic response generator then takes the prototype and the desired language style as model input to obtain a high-quality and stylistic response.
no code implementations • 1 Apr 2020 • Guodong Xu, Wenxiao Wang, Zili Liu, Liang Xie, Zheng Yang, Haifeng Liu, Deng Cai
3D object detection based on point clouds has become more and more popular.
no code implementations • 14 Jan 2020 • Boyuan Pan, Yazheng Yang, Zhou Zhao, Yueting Zhuang, Deng Cai
Neural Machine Translation (NMT) has become a popular technology in recent years, and the encoder-decoder framework is the mainstream among all the methods.
1 code implementation • 4 Jan 2020 • Minghao Chen, Shuai Zhao, Haifeng Liu, Deng Cai
In order to combine the strengths of these two methods, we propose a novel method called Adversarial-Learned Loss for Domain Adaptation (ALDA).
no code implementations • 21 Dec 2019 • Wenxiao Wang, Shuai Zhao, Minghao Chen, Jinming Hu, Deng Cai, Haifeng Liu
The dominant pruning methods, filter-level pruning methods, evaluate their performance through the reduction ratio of computations and deem that a higher reduction ratio of computations is equivalent to a higher acceleration ratio in terms of inference time.
1 code implementation • 18 Nov 2019 • Deng Cai, Wai Lam
The dominant graph-to-sequence transduction models employ graph neural networks for graph representation learning, where the structural information is reflected by the receptive field of neurons.
no code implementations • 14 Nov 2019 • Liang Xie, Chao Xiang, Zhengxu Yu, Guodong Xu, Zheng Yang, Deng Cai, Xiaofei He
Moreover, based on the PACF module, we propose a 3D multi-sensor multi-task network called Pointcloud-Image RCNN(PI-RCNN as brief), which handles the image segmentation and 3D object detection tasks.
no code implementations • IJCNLP 2019 • Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Shuming Shi
End-to-end sequence generation is a popular technique for developing open domain dialogue systems, though they suffer from the \textit{safe response problem}.
2 code implementations • NeurIPS 2019 • Shuai Zhao, Yang Wang, Zheng Yang, Deng Cai
In this paper, we develop a region mutual information (RMI) loss to model the dependencies among pixels more simply and efficiently.
no code implementations • 19 Oct 2019 • Shuai Zhao, Boxi Wu, Wenqing Chu, Yao Hu, Deng Cai
Inspired by the widely-used structural similarity (SSIM) index in image quality assessment, we use the linear correlation between two images to quantify their structural similarity.
1 code implementation • ICCV 2019 • Minghao Chen, Hongyang Xue, Deng Cai
However, when applying the entropy minimization to UDA for semantic segmentation, the gradient of the entropy is biased towards samples that are easy to transfer.
1 code implementation • IJCNLP 2019 • Deng Cai, Wai Lam
The output graph spans the nodes by the distance to the root, following the intuition of first grasping the main ideas then digging into more details.
Ranked #25 on AMR Parsing on LDC2017T10
2 code implementations • 5 Sep 2019 • Hongyang Xue, Wenqing Chu, Zhou Zhao, Deng Cai
We propose a new attention model for video question answering.
6 code implementations • 2 Sep 2019 • Zili Liu, Tu Zheng, Guodong Xu, Zheng Yang, Haifeng Liu, Deng Cai
Experiments on MS COCO show that our TTFNet has great advantages in balancing training time, inference speed, and accuracy.
no code implementations • IJCNLP 2019 • Huajie Chen, Deng Cai, Wei Dai, Zehui Dai, Yadong Ding
Judgment prediction for legal cases has attracted much research efforts for its practice use, of which the ultimate goal is prison term prediction.
no code implementations • 13 Aug 2019 • Huayang Li, Guoping Huang, Deng Cai, Lemao Liu
Experiments show that our approach can indeed improve the translation quality with the automatically generated constraints.
1 code implementation • 7 Aug 2019 • Zhengxu Yu, Dong Shen, Zhongming Jin, Jianqiang Huang, Deng Cai, Xian-Sheng Hua
Model fine-tuning is a widely used transfer learning approach in person Re-identification (ReID) applications, which fine-tuning a pre-trained feature extraction model into the target scenario instead of training a model from scratch.
1 code implementation • ACL 2019 • Boyuan Pan, Hao Li, Ziyu Yao, Deng Cai, Huan Sun
This paper investigates a new task named Conversational Question Generation (CQG) which is to generate a question based on a passage and a conversation history (i. e., previous turns of question-answer pairs).
1 code implementation • ACL 2018 • Boyuan Pan, Yazheng Yang, Zhou Zhao, Yueting Zhuang, Deng Cai, Xiaofei He
We observe that people usually use some discourse markers such as "so" or "but" to represent the logical relationship between two sentences.
Ranked #13 on Natural Language Inference on SNLI
no code implementations • NeurIPS 2018 • Boyuan Pan, Yazheng Yang, Hao Li, Zhou Zhao, Yueting Zhuang, Deng Cai, Xiaofei He
In this paper, we transfer knowledge learned from machine comprehension to the sequence-to-sequence tasks to deepen the understanding of the text.
no code implementations • 16 Jul 2019 • Boxi Wu, Shuai Zhao, Wenqing Chu, Zheng Yang, Deng Cai
To be specific, our method explicitly requires the network to predict semantic segmentation as well as dilated affinity, which is a sparse version of pair-wise pixel affinity.
2 code implementations • 13 Jul 2019 • Cong Fu, Changxu Wang, Deng Cai
However, we find there are several limitations with NSG: 1) NSG has no theoretical guarantee on nearest neighbor search when the query is not indexed in the database; 2) NSG is too sparse which harms the search performance.
no code implementations • 1 Jul 2019 • Bo wang, Minghui Qiu, Xisen Wang, Yaliang Li, Yu Gong, Xiaoyi Zeng, Jung Huang, Bo Zheng, Deng Cai, Jingren Zhou
To the best of our knowledge, this is the first to build a minimax game based model for selective transfer learning.
no code implementations • 28 Jun 2019 • Zhu Zhang, Zhou Zhao, Zhijie Lin, Jingkuan Song, Deng Cai
Thus, we consider a new task to localize unseen activities in videos via image queries, named Image-Based Activity Localization.
1 code implementation • 25 Jun 2019 • Wenxiao Wang, Cong Fu, Jishun Guo, Deng Cai, Xiaofei He
2) Cross-layer filter comparison is unachievable since the importance is defined locally within each layer.
1 code implementation • 24 Jun 2019 • Yu Zhu, Yu Gong, Qingwen Liu, Yingcai Ma, Wenwu Ou, Junxiong Zhu, Beidou Wang, Ziyu Guan, Deng Cai
A novel query-based interactive recommender system is proposed in this paper, where \textbf{personalized questions are accurately generated from millions of automatically constructed questions} in Step 1, and \textbf{the recommendation is ensured to be closely-related to users' feedback} in Step 2.
1 code implementation • 13 May 2019 • Wenqing Chu, Wei-Chih Hung, Yi-Hsuan Tsai, Deng Cai, Ming-Hsuan Yang
However, current state-of-the-art face parsing methods require large amounts of labeled data on the pixel-level and such process for caricature is tedious and labor-intensive.
no code implementations • 18 Jan 2019 • Hai Zhao, Deng Cai, Changning Huang, Chunyu Kit
This paper reviews the development of Chinese word segmentation (CWS) in the most recent decade, 2007-2017.
1 code implementation • 14 Nov 2018 • Lei Wang, Yan Wang, Deng Cai, Dongxiang Zhang, Xiaojiang Liu
Moreover, we analyze the performance of three popular SEQ2SEQ models on the math word problem solving.
no code implementations • 1 Nov 2018 • Haojie Pan, Junpei Zhou, Zhou Zhao, Yan Liu, Deng Cai, Min Yang
We first propose a new task named Dialogue Description (Dial2Desc).
no code implementations • 24 Oct 2018 • Zhou Zhao, Hanbing Zhan, Lingtao Meng, Jun Xiao, Jun Yu, Min Yang, Fei Wu, Deng Cai
In this paper, we study the problem of image retweet prediction in social media, which predicts the image sharing behavior that the user reposts the image tweets from their followees.
no code implementations • EMNLP 2018 • Lei Wang, Yan Wang, Deng Cai, Dongxiang Zhang, Xiaojiang Liu
Moreover, we analyze the performance of three popular SEQ2SEQ models on the math word problem solving.
1 code implementation • NAACL 2019 • Deng Cai, Yan Wang, Victoria Bi, Zhaopeng Tu, Xiaojiang Liu, Wai Lam, Shuming Shi
Such models rely on insufficient information for generating a specific response since a certain query could be answered in multiple ways.
no code implementations • 13 Aug 2018 • Yanpeng Zhao, Wei Bi, Deng Cai, Xiaojiang Liu, Kewei Tu, Shuming Shi
Then, by recombining the content with the target style, we decode a sentence aligned in the target domain.
no code implementations • 23 May 2018 • Yu Zhu, Junxiong Zhu, Jie Hou, Yongliang Li, Beidou Wang, Ziyu Guan, Deng Cai
In e-commerce websites like Taobao, brand is playing a more important role in influencing users' decision of click/purchase, partly because users are now attaching more importance to the quality of products and brand is an indicator of quality.
no code implementations • 23 May 2018 • Yu Zhu, Jinhao Lin, Shibi He, Beidou Wang, Ziyu Guan, Haifeng Liu, Deng Cai
Both content information (e. g. item attributes) and initial user ratings are valuable for seizing users' preferences on a new item.
5 code implementations • 4 Jan 2018 • Dan Deng, Haifeng Liu, Xuelong. Li, Deng Cai
Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression.
Ranked #6 on Scene Text Detection on ICDAR 2013
1 code implementation • 20 Dec 2017 • Zichen Yang, Haifeng Liu, Deng Cai
Experimental results show that images synthesized by our approach are significantly more diverse than that of the current existing works and equipping our diversity loss does not degrade the reality of the base networks.
no code implementations • 16 Nov 2017 • Deng Cai, Xiuye Gu, Chaoqi Wang
However, there are serious flaws in the evaluations of existing deep hashing papers: (1) The datasets they used are too small and simple to simulate the real CBIR situation.
no code implementations • SIGIR 2018 • Zheqian Chen, Rongqin Yang, Zhou Zhao, Deng Cai, Xiaofei He
Dialogue Act Recognition (DAR) is a challenging problem in dialogue interpretation, which aims to attach semantic labels to utterances and characterize the speaker's intention.
no code implementations • 1 Nov 2017 • Boyuan Pan, Hao Li, Zhou Zhao, Deng Cai, Xiaofei He
In this paper, we propose a novel neural network system that consists a Demand Optimization Model based on a passage-attention neural machine translation and a Reader Model that can find the answer given the optimized question.
no code implementations • 8 Oct 2017 • Zheqian Chen, Rongqin Yang, Bin Cao, Zhou Zhao, Deng Cai, Xiaofei He
Machine Comprehension (MC) is a challenging task in Natural Language Processing field, which aims to guide the machine to comprehend a passage and answer the given question.
Ranked #33 on Question Answering on SQuAD1.1 dev
2 code implementations • 12 Sep 2017 • Junying Li, Deng Cai, Xiaofei He
Molecules can be represented as an undirected graph, and we can utilize graph convolution networks to predication molecular properties.
Ranked #1 on Drug Discovery on HIV dataset
no code implementations • 28 Jul 2017 • Boyuan Pan, Hao Li, Zhou Zhao, Bin Cao, Deng Cai, Xiaofei He
Machine comprehension(MC) style question answering is a representative problem in natural language processing.
Ranked #37 on Question Answering on TriviaQA
2 code implementations • 1 Jul 2017 • Cong Fu, Chao Xiang, Changxu Wang, Deng Cai
In this paper, to further improve the search-efficiency and scalability of graph-based methods, we start by introducing four aspects: (1) ensuring the connectivity of the graph; (2) lowering the average out-degree of the graph for fast traversal; (3) shortening the search path; and (4) reducing the index size.
2 code implementations • 24 May 2017 • Junying Li, Zichen Yang, Haifeng Liu, Deng Cai
Recently, learning equivariant representations has attracted considerable research attention.
no code implementations • 3 May 2017 • Hongyang Xue, Zhou Zhao, Deng Cai
Then we propose a TGIF-QA dataset for video question answering with the help of automatic question generation.
1 code implementation • ACL 2017 • Deng Cai, Hai Zhao, Zhisong Zhang, Yuan Xin, Yongjian Wu, Feiyue Huang
Neural models with minimal feature engineering have achieved competitive performance against traditional methods for the task of Chinese word segmentation.
2 code implementations • 22 Dec 2016 • Deng Cai
However, many existing hashing papers only report the performance with the code length shorter than 128.
no code implementations • 24 Nov 2016 • Zheqian Chen, Ben Gao, Huimin Zhang, Zhou Zhao, Deng Cai
However, it is not effective for users to attain answers within minutes.
no code implementations • 24 Nov 2016 • Zheqian Chen, Chi Zhang, Zhou Zhao, Deng Cai
The challenges in this task are the lexical gaps between questions for the word ambiguity and word mismatch problem.
no code implementations • 16 Nov 2016 • Ping Li, Jiajun Bu, Chun Chen, Zhanying He, Deng Cai
In this study, we focus on improving the co-clustering performance via manifold ensemble learning, which is able to maximally approximate the intrinsic manifolds of both the sample and feature spaces.
no code implementations • 15 Nov 2016 • Ping Li, Jun Yu, Meng Wang, Luming Zhang, Deng Cai, Xuelong. Li
To achieve this goal, we cast the problem into a constrained rank minimization framework by adopting the least squares regularization.
5 code implementations • 23 Sep 2016 • Cong Fu, Deng Cai
In this paper, we propose EFANNA, an extremely fast approximate nearest neighbor search algorithm based on $k$NN Graph.
1 code implementation • ICML 2017 • Weizhong Zhang, Bin Hong, Wei Liu, Jieping Ye, Deng Cai, Xiaofei He, Jie Wang
By noting that sparse SVMs induce sparsities in both feature and sample spaces, we propose a novel approach, which is based on accurate estimations of the primal and dual optima of sparse SVMs, to simultaneously identify the inactive features and samples that are guaranteed to be irrelevant to the outputs.
1 code implementation • ACL 2016 • Deng Cai, Hai Zhao
Most previous approaches to Chinese word segmentation formalize this problem as a character-based sequence labeling task where only contextual information within fixed sized local windows and simple interactions between adjacent tags can be captured.
1 code implementation • 20 Apr 2016 • Hongyang Xue, Shengming Zhang, Deng Cai
The proposed low gradient regularization is integrated with the low rank regularization into the low rank low gradient approach for depth image inpainting.
no code implementations • 14 Apr 2016 • Wenqing Chu, Deng Cai
Object detection is one of the most active areas in computer vision, which has made significant improvement in recent years.
no code implementations • 15 Jan 2016 • Hongyang Xue, Deng Cai
For the first step they solve a fully connected MRF model.
no code implementations • CVPR 2013 • Yue Lin, Rong Jin, Deng Cai, Shuicheng Yan, Xuelong. Li
Recent studies have shown that hashing methods are effective for high dimensional nearest neighbor search.
no code implementations • IEEE Transactions on Pattern Analysis and Machine Intelligence 2011 • Deng Cai, Xiaofei He, Jiawei Han, Thomas S. Huang
In GNMF, an affinity graph is constructed to encode the geometrical information and we seek a matrix factorization, which respects the graph structure.