no code implementations • 18 Apr 2024 • Shengcao Cao, Jiuxiang Gu, Jason Kuen, Hao Tan, Ruiyi Zhang, Handong Zhao, Ani Nenkova, Liang-Yan Gui, Tong Sun, Yu-Xiong Wang
Using raw images as the sole training data, our method achieves unprecedented performance in self-supervised open-world segmentation, marking a significant milestone towards high-quality open-world entity segmentation in the absence of human-annotated masks.
no code implementations • 18 Apr 2024 • Xinyue Wei, Kai Zhang, Sai Bi, Hao Tan, Fujun Luan, Valentin Deschaintre, Kalyan Sunkavalli, Hao Su, Zexiang Xu
This allows for end-to-end mesh reconstruction by fine-tuning a pre-trained NeRF LRM with mesh rendering.
no code implementations • 31 Jan 2024 • Hao Tan, Zichang Tan, Jun Li, Jun Wan, Zhen Lei
In contrast to the unidirectional fusion in previous works, we introduce a Dual-Modal Attention (DMA) that enables bidirectional interaction between textual and visual features, yielding context-aware label representations and semantic-related visual representations, which are subsequently used to calculate similarities and generate final predictions for all labels.
no code implementations • 22 Jan 2024 • Zhenzhen Weng, Jingyuan Liu, Hao Tan, Zhan Xu, Yang Zhou, Serena Yeung-Levy, Jimei Yang
We present Human-LRM, a diffusion-guided feed-forward model that predicts the implicit field of a human from a single image.
no code implementations • 21 Dec 2023 • Desai Xie, Jiahao Li, Hao Tan, Xin Sun, Zhixin Shu, Yi Zhou, Sai Bi, Sören Pirk, Arie E. Kaufman
To this end, we introduce Carve3D, an improved RLFT algorithm coupled with a novel Multi-view Reconstruction Consistency (MRC) metric, to enhance the consistency of multi-view diffusion models.
1 code implementation • 11 Dec 2023 • Hao Tan, Jun Li, Yizhuang Zhou, Jun Wan, Zhen Lei, Xiangyu Zhang
We introduce text supervision to the optimization of prompts, which enables two benefits: 1) releasing the model reliance on the pre-defined category names during inference, thereby enabling more flexible prompt generation; 2) reducing the number of inputs to the text encoder, which decreases GPU memory consumption significantly.
no code implementations • 20 Nov 2023 • Peng Wang, Hao Tan, Sai Bi, Yinghao Xu, Fujun Luan, Kalyan Sunkavalli, Wenping Wang, Zexiang Xu, Kai Zhang
We propose a Pose-Free Large Reconstruction Model (PF-LRM) for reconstructing a 3D object from a few unposed images even with little visual overlap, while simultaneously estimating the relative camera poses in ~1. 3 seconds on a single A100 GPU.
no code implementations • 15 Nov 2023 • Yinghao Xu, Hao Tan, Fujun Luan, Sai Bi, Peng Wang, Jiahao Li, Zifan Shi, Kalyan Sunkavalli, Gordon Wetzstein, Zexiang Xu, Kai Zhang
We propose \textbf{DMV3D}, a novel 3D generation approach that uses a transformer-based 3D large reconstruction model to denoise multi-view diffusion.
no code implementations • 14 Nov 2023 • Yuwei Wang, Runhan Li, Hao Tan, Xuefeng Jiang, Sheng Sun, Min Liu, Bo Gao, Zhiyuan Wu
By fusing the logits of the two models, the private weak learner can capture the variance of different data, regardless of their category.
no code implementations • 10 Nov 2023 • Jiahao Li, Hao Tan, Kai Zhang, Zexiang Xu, Fujun Luan, Yinghao Xu, Yicong Hong, Kalyan Sunkavalli, Greg Shakhnarovich, Sai Bi
Text-to-3D with diffusion models has achieved remarkable progress in recent years.
1 code implementation • 8 Nov 2023 • Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, Hao Tan
We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds.
1 code implementation • ICCV 2023 • Zun Wang, Jialu Li, Yicong Hong, Yi Wang, Qi Wu, Mohit Bansal, Stephen Gould, Hao Tan, Yu Qiao
Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents.
no code implementations • 24 Jul 2023 • Viet Dac Lai, Abel Salinas, Hao Tan, Trung Bui, Quan Tran, Seunghyun Yoon, Hanieh Deilamsalehy, Franck Dernoncourt, Thien Huu Nguyen
Punctuation restoration is an important task in automatic speech recognition (ASR) which aim to restore the syntactic structure of generated ASR texts to improve readability.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • ICCV 2023 • Yicong Hong, Yang Zhou, Ruiyi Zhang, Franck Dernoncourt, Trung Bui, Stephen Gould, Hao Tan
Being able to perceive the semantics and the spatial structure of the environment is essential for visual navigation of a household robot.
1 code implementation • 9 Jun 2023 • Fuxiao Liu, Hao Tan, Chris Tensmeyer
In this work, we propose DocumentCLIP, a salience-aware contrastive learning framework to enforce vision-language pretraining models to comprehend the interaction between images and longer text within documents.
1 code implementation • 19 May 2023 • Zhe Chen, Hao Tan, Tao Wang, Tianrun Shen, Tong Lu, Qiuying Peng, Cheng Cheng, Yue Qi
The core insight of our method is to fully consider the information propagation among nodes and edges in a graph when building the attention module in the transformer blocks.
Ranked #2 on Graph Regression on PCQM4M-LSC (Validation MAE metric)
no code implementations • 18 Oct 2022 • Hongyu Zhao, Hao Tan, Hongyuan Mei
Our tiny-attention adapter learns to modify the hidden states at each position directly conditioned on the hidden states at all the other positions, which is missed by the previously proposed adapters.
no code implementations • 3 Aug 2022 • Xiao Zhang, Hao Tan, Xuan Huang, Denghui Zhang, Keke Tang, Zhaoquan Gu
With the development of hardware and algorithms, ASR(Automatic Speech Recognition) systems evolve a lot.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • Findings (NAACL) 2022 • Jialu Li, Hao Tan, Mohit Bansal
Empirically, on the Room-Across-Room dataset, we show that our multilingual agent gets large improvements in all metrics over the strong baseline model when generalizing to unseen environments with the cross-lingual language representation and the environment-agnostic visual representation.
1 code implementation • CVPR 2022 • Jialu Li, Hao Tan, Mohit Bansal
Training on these edit-augmented environments prevents the agent from overfitting to existing environments and helps generalize better to new, unseen environments.
Ranked #2 on Vision and Language Navigation on RxR (using extra training data)
4 code implementations • 13 Jul 2021 • Sheng Shen, Liunian Harold Li, Hao Tan, Mohit Bansal, Anna Rohrbach, Kai-Wei Chang, Zhewei Yao, Kurt Keutzer
Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world.
Ranked #4 on Vision and Language Navigation on RxR (using extra training data)
1 code implementation • NeurIPS 2021 • Zineng Tang, Jaemin Cho, Hao Tan, Mohit Bansal
We train a multi-modal teacher model on a video-text dataset, and then transfer its knowledge to a student language model with a text dataset.
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 #10 on Action Recognition on Diving-48
1 code implementation • NAACL 2021 • Jialu Li, Hao Tan, Mohit Bansal
One key challenge in this task is to ground instructions with the current visual information that the agent perceives.
2 code implementations • 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 • Findings of the Association for Computational Linguistics 2020 • Hyounghun Kim, Abhay Zala, Graham Burri, Hao Tan, Mohit Bansal
During this task, the agent (similar to a PokeMON GO player) is asked to find and collect different target objects one-by-one by navigating based on natural language instructions in a complex, realistic outdoor environment, but then also ARRAnge the collected objects part-by-part in an egocentric grid-layout environment.
1 code implementation • EMNLP 2020 • Hao Tan, Mohit Bansal
We find that the main reason hindering this exploration is the large divergence in magnitude and distributions between the visually-grounded language datasets and pure-language corpora.
1 code implementation • EMNLP 2020 • Qinxin Wang, Hao Tan, Sheng Shen, Michael W. Mahoney, Zhewei Yao
Phrase localization is a task that studies the mapping from textual phrases to regions of an image.
2 code implementations • 14 Sep 2020 • Hao Tan, Ran Cheng, Shihua Huang, Cheng He, Changxiao Qiu, Fan Yang, Ping Luo
Despite the remarkable successes of Convolutional Neural Networks (CNNs) in computer vision, it is time-consuming and error-prone to manually design a CNN.
1 code implementation • 6 May 2020 • Yubo Zhang, Hao Tan, Mohit Bansal
Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions, explore the given environments, and reach the desired target locations.
1 code implementation • EMNLP 2020 • Xiang Zhou, Yixin Nie, Hao Tan, Mohit Bansal
For the first question, we conduct a thorough empirical study over analysis sets and find that in addition to the unstable final performance, the instability exists all along the training curve.
no code implementations • 17 Jan 2020 • Hyounghun Kim, Hao Tan, Mohit Bansal
The Visual Dialog task requires a model to exploit both image and conversational context information to generate the next response to the dialogue.
9 code implementations • IJCNLP 2019 • Hao Tan, Mohit Bansal
In LXMERT, we build a large-scale Transformer model that consists of three encoders: an object relationship encoder, a language encoder, and a cross-modality encoder.
Ranked #1 on Visual Question Answering (VQA) on VizWiz 2018
1 code implementation • ACL 2019 • Hao Tan, Franck Dernoncourt, Zhe Lin, Trung Bui, Mohit Bansal
To push forward the research in this direction, we first introduce a new language-guided image editing dataset that contains a large number of real image pairs with corresponding editing instructions.
no code implementations • 29 Apr 2019 • Haonan Chen, Hao Tan, Alan Kuntz, Mohit Bansal, Ron Alterovitz
Our results show the feasibility of a robot learning commonsense knowledge automatically from web-based textual corpora, and the power of learned commonsense reasoning models in enabling a robot to autonomously perform tasks based on incomplete natural language instructions.
1 code implementation • NAACL 2019 • Hao Tan, Licheng Yu, Mohit Bansal
Next, we apply semi-supervised learning (via back-translation) on these dropped-out environments to generate new paths and instructions.
Ranked #1 on Vision-Language Navigation on Room2Room
no code implementations • NAACL 2018 • Hao Tan, Mohit Bansal
Visual reasoning with compositional natural language instructions, e. g., based on the newly-released Cornell Natural Language Visual Reasoning (NLVR) dataset, is a challenging task, where the model needs to have the ability to create an accurate mapping between the diverse phrases and the several objects placed in complex arrangements in the image.
no code implementations • 12 Jul 2017 • Hao Tan, Mohit Bansal
Models that can execute natural language instructions for situated robotic tasks such as assembly and navigation have several useful applications in homes, offices, and remote scenarios.
2 code implementations • CVPR 2017 • Licheng Yu, Hao Tan, Mohit Bansal, Tamara L. Berg
The speaker generates referring expressions, the listener comprehends referring expressions, and the reinforcer introduces a reward function to guide sampling of more discriminative expressions.