1 code implementation • NAACL (ACL) 2022 • Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji
We introduce RESIN-11, a new schema-guided event extraction&prediction framework that can be applied to a large variety of newsworthy scenarios.
no code implementations • 10 Apr 2023 • Lin Chen, Zhijie Jia, Tian Qiu, Lechao Cheng, Jie Lei, Zunlei Feng, Mingli Song
In this work, we propose a new paradigm dubbed Decision Stream Calibration that boosts the performance of general Vision Transformers.
no code implementations • 9 Apr 2023 • Wenxiang Xu, Linyun Zhou, Lin Chen, Lechao Cheng, Jie Lei, Zunlei Feng, Mingli Song
This is specifically achieved by devising an elaborated ``prophetic'' teacher, termed as ``Propheter'', that aims to learn the potential class distributions.
no code implementations • 15 Feb 2023 • Jie Lei, José Flich, Enrique S. Quintana-Ortí
The remarkable positive impact of Deep Neural Networks on many Artificial Intelligence (AI) tasks has led to the development of various high performance algorithms as well as specialized processors and accelerators.
1 code implementation • CVPR 2023 • Weiying Xie, Kai Jiang, Yunsong Li, Jie Lei, Leyuan Fang, Wen-jin Guo
Specifically, we create a positive cycle between fusion and degradation estimation under a new probabilistic framework.
no code implementations • CVPR 2023 • Shengxuming Zhang, Tianqi Shi, Yang Jiang, Xiuming Zhang, Jie Lei, Zunlei Feng, Mingli Song
The loopback between two branches enables the category label to supervise the cell locating branch to learn the locating ability for cancerous areas.
1 code implementation • 31 Dec 2022 • Jiaqing Zhang, Jie Lei, Weiying Xie, Yunsong Li, Xiuping Jia
More concretely, we first design a structure called guided quantization self-distillation (GQSD), which is an innovative idea for realizing lightweight through the synergy of quantization and distillation.
1 code implementation • CVPR 2023 • Yan-Bo Lin, Yi-Lin Sung, Jie Lei, Mohit Bansal, Gedas Bertasius
To do so, we propose a latent audio-visual hybrid (LAVISH) adapter that adapts pretrained ViTs to audio-visual tasks by injecting a small number of trainable parameters into every layer of a frozen ViT.
Ranked #2 on
Audio-visual Question Answering
on MUSIC-AVQA
1 code implementation • CVPR 2023 • Feng Cheng, Xizi Wang, Jie Lei, David Crandall, Mohit Bansal, Gedas Bertasius
Furthermore, our model also obtains state-of-the-art video question-answering results on ActivityNet-QA, MSRVTT-QA, MSRVTT-MC and TVQA.
1 code implementation • 21 Nov 2022 • Zineng Tang, Jaemin Cho, Jie Lei, Mohit Bansal
We present Perceiver-VL, a vision-and-language framework that efficiently handles high-dimensional multimodal inputs such as long videos and text.
1 code implementation • 27 Sep 2022 • Jiaqing Zhang, Jie Lei, Weiying Xie, Zhenman Fang, Yunsong Li, Qian Du
Furthermore, we design a simple and flexible SR branch to learn HR feature representations that can discriminate small objects from vast backgrounds with low-resolution (LR) input, thus further improving the detection accuracy.
Ranked #1 on
Object Detection
on VEDAI
1 code implementation • 27 Jul 2022 • Jie Lei, Zhao Liu, Zeyu Zou, Tong Li, Xu Juan, Shuaiwei Wang, Guoyu Yang, Zunlei Feng
On the other hand, GUS is introduced to suppress the feature ambiguity in the representation space.
2 code implementations • 7 Jun 2022 • Jie Lei, Tamara L. Berg, Mohit Bansal
Training an effective video-and-language model intuitively requires multiple frames as model inputs.
Ranked #3 on
Zero-Shot Video Retrieval
on ActivityNet
(using extra training data)
1 code implementation • 22 May 2022 • Zhenhailong Wang, Manling Li, Ruochen Xu, Luowei Zhou, Jie Lei, Xudong Lin, Shuohang Wang, ZiYi Yang, Chenguang Zhu, Derek Hoiem, Shih-Fu Chang, Mohit Bansal, Heng Ji
The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
1 code implementation • 6 Apr 2022 • Yan-Bo Lin, Jie Lei, Mohit Bansal, Gedas Bertasius
We introduce an audiovisual method for long-range text-to-video retrieval.
no code implementations • 25 Mar 2022 • Jiacong Hu, Jing Gao, Zunlei Feng, Lechao Cheng, Jie Lei, Hujun Bao, Mingli Song
the feature maps are adopted to locate the critical features in each layer.
no code implementations • 10 Mar 2022 • Jie Lei, Xinlei Chen, Ning Zhang, Mengjiao Wang, Mohit Bansal, Tamara L. Berg, Licheng Yu
In this work, we propose LoopITR, which combines them in the same network for joint learning.
1 code implementation • 15 Dec 2021 • Li Xu, Gang He, Jinjia Zhou, Jie Lei, Weiying Xie, Yunsong Li, Yu-Wing Tai
In most video platforms, such as Youtube, and TikTok, the played videos usually have undergone multiple video encodings such as hardware encoding by recording devices, software encoding by video editing apps, and single/multiple video transcoding by video application servers.
1 code implementation • NeurIPS 2021 • Jie Lei, Tamara Berg, Mohit Bansal
Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w. r. t.
no code implementations • 1 Aug 2021 • Lechao Cheng, Zunlei Feng, Xinchao Wang, Ya Jie Liu, Jie Lei, Mingli Song
In this paper, we introduce a novel Reference semantic segmentation Network (Ref-Net) to conduct visual boundary knowledge translation.
1 code implementation • 1 Aug 2021 • Zunlei Feng, Zhonghua Wang, Xinchao Wang, Xiuming Zhang, Lechao Cheng, Jie Lei, Yuexuan Wang, Mingli Song
The diagnosis of MVI needs discovering the vessels that contain hepatocellular carcinoma cells and counting their number in each vessel, which depends heavily on experiences of the doctor, is largely subjective and time-consuming.
1 code implementation • ACL 2021 • Jie Lei, Tamara L. Berg, Mohit Bansal
We introduce mTVR, a large-scale multilingual video moment retrieval dataset, containing 218K English and Chinese queries from 21. 8K TV show video clips.
3 code implementations • 20 Jul 2021 • Jie Lei, Tamara L. Berg, Mohit Bansal
Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w. r. t.
Ranked #2 on
Moment Retrieval
on Charades-STA
1 code implementation • 21 Jun 2021 • Hao Tan, Jie Lei, Thomas Wolf, Mohit Bansal
Unlike language, where the text tokens are more independent, neighboring video tokens typically have strong correlations (e. g., consecutive video frames usually look very similar), and hence uniformly masking individual tokens will make the task too trivial to learn useful representations.
Ranked #6 on
Action Recognition
on Diving-48
1 code implementation • 8 Jun 2021 • Linjie Li, Jie Lei, Zhe Gan, Licheng Yu, Yen-Chun Chen, Rohit Pillai, Yu Cheng, Luowei Zhou, Xin Eric Wang, William Yang Wang, Tamara Lee Berg, Mohit Bansal, Jingjing Liu, Lijuan Wang, Zicheng Liu
Most existing video-and-language (VidL) research focuses on a single dataset, or multiple datasets of a single task.
1 code implementation • NAACL 2021 • Zineng Tang, Jie Lei, Mohit Bansal
Second, to alleviate the temporal misalignment issue, our method incorporates an entropy minimization-based constrained attention loss, to encourage the model to automatically focus on the correct caption from a pool of candidate ASR captions.
no code implementations • ICCV 2021 • Linjie Li, Jie Lei, Zhe Gan, Jingjing Liu
We hope our Adversarial VQA dataset can shed new light on robustness study in the community and serve as a valuable benchmark for future work.
1 code implementation • CVPR 2021 • Jie Lei, Linjie Li, Luowei Zhou, Zhe Gan, Tamara L. Berg, Mohit Bansal, Jingjing Liu
Experiments on text-to-video retrieval and video question answering on six datasets demonstrate that ClipBERT outperforms (or is on par with) existing methods that exploit full-length videos, suggesting that end-to-end learning with just a few sparsely sampled clips is often more accurate than using densely extracted offline features from full-length videos, proving the proverbial less-is-more principle.
Ranked #20 on
Visual Question Answering (VQA)
on MSRVTT-QA
(using extra training data)
1 code implementation • 4 Feb 2021 • Jaemin Cho, Jie Lei, Hao Tan, Mohit Bansal
On 7 popular vision-and-language benchmarks, including visual question answering, referring expression comprehension, visual commonsense reasoning, most of which have been previously modeled as discriminative tasks, our generative approach (with a single unified architecture) reaches comparable performance to recent task-specific state-of-the-art vision-and-language models.
Ranked #3 on
Image Captioning
on nocaps val
no code implementations • ICCV 2021 • Zunlei Feng, Zhonghua Wang, Xinchao Wang, Yining Mao, Thomas Li, Jie Lei, Yuexuan Wang, Mingli Song
The existing two unsupervised methods are prone to failure on degenerated samples.
no code implementations • 1 Jan 2021 • Tao Jiang, Weiying Xie, Jie Lei, Yunsong Li, Zan Li
For solving these problems, this paper proposes a sparse coding-inspired generative adversarial network (GAN) for weakly supervised HAD, named sparseHAD.
no code implementations • 1 Jan 2021 • Jiaping Zhong, Weiying Xie, Jie Lei, Yunsong Li, Zan Li
Hyperspectral anomaly detection under high-dimensional data and interference of deteriorated bands without any prior information has been challenging and attracted close attention in the exploration of the unknown in real scenarios.
no code implementations • NeurIPS 2020 • Zunlei Feng, Yongming He, Xinchao Wang, Xin Gao, Jie Lei, Cheng Jin, Mingli Song
In this paper, we introduce the One-sample Guided Object Representation Disassembling (One-GORD) method, which only requires one annotated sample for each object category to learn disassembled object representation from unannotated images.
1 code implementation • EMNLP 2020 • Jie Lei, Licheng Yu, Tamara L. Berg, Mohit Bansal
Given a video with aligned dialogue, people can often infer what is more likely to happen next.
no code implementations • 4 Jul 2020 • K. Darshana Abeyrathna, Ole-Christoffer Granmo, Rishad Shafik, Alex Yakovlev, Adrian Wheeldon, Jie Lei, Morten Goodwin
However, TMs rely heavily on energy-costly random number generation to stochastically guide a team of Tsetlin Automata to a Nash Equilibrium of the TM game.
1 code implementation • ACL 2020 • Jie Lei, Li-Wei Wang, Yelong Shen, Dong Yu, Tamara L. Berg, Mohit Bansal
Generating multi-sentence descriptions for videos is one of the most challenging captioning tasks due to its high requirements for not only visual relevance but also discourse-based coherence across the sentences in the paragraph.
Ranked #5 on
Video Captioning
on ActivityNet Captions
2 code implementations • ECCV 2020 • Jie Lei, Licheng Yu, Tamara L. Berg, Mohit Bansal
The queries are also labeled with query types that indicate whether each of them is more related to video or subtitle or both, allowing for in-depth analysis of the dataset and the methods that built on top of it.
Ranked #2 on
Video Retrieval
on TVR
3 code implementations • ACL 2020 • Jie Lei, Licheng Yu, Tamara L. Berg, Mohit Bansal
We present the task of Spatio-Temporal Video Question Answering, which requires intelligent systems to simultaneously retrieve relevant moments and detect referenced visual concepts (people and objects) to answer natural language questions about videos.
Ranked #4 on
Video Question Answering
on TVQA
4 code implementations • EMNLP 2018 • Jie Lei, Licheng Yu, Mohit Bansal, Tamara L. Berg
Recent years have witnessed an increasing interest in image-based question-answering (QA) tasks.
Ranked #3 on
Video Question Answering
on SUTD-TrafficQA
no code implementations • ECCV 2018 • Jie Song, Chengchao Shen, Jie Lei, An-Xiang Zeng, Kairi Ou, DaCheng Tao, Mingli Song
We propose a selective zero-shot classifier based on both the human defined and the automatically discovered residual attributes.
no code implementations • 14 Nov 2017 • Gongze Cao, Yezhou Yang, Jie Lei, Cheng Jin, Yang Liu, Mingli Song
As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts.