no code implementations • 9 Jun 2023 • Eduardo R. Corral-Soto, Alaap Grandhi, Yannis Y. He, Mrigank Rochan, Bingbing Liu
In recent years, much progress has been made in LiDAR-based 3D object detection mainly due to advances in detector architecture designs and availability of large-scale LiDAR datasets.
no code implementations • 18 Oct 2022 • Mrigank Rochan, Xingxin Chen, Alaap Grandhi, Eduardo R. Corral-Soto, Bingbing Liu
The idea is to initiate the training with the batch of samples from the source and target domain data in an alternate fashion, but then gradually reduce the amount of the source domain data over time as the training progresses.
no code implementations • 14 Jan 2022 • Eduardo R. Corral-Soto, Mrigank Rochan, Yannis Y. He, Shubhra Aich, Yang Liu, Liu Bingbing
We consider the setting where we have a fully-labeled data set from source domain and a target domain with a few labeled and many unlabeled examples.
no code implementations • CVPR 2022 • Taivanbat Badamdorj, Mrigank Rochan, Yang Wang, Li Cheng
Our framework encodes a video into a vector representation by learning to pick video clips that help to distinguish it from other videos via a contrastive objective using dropout noise.
no code implementations • 20 Jul 2021 • Mrigank Rochan, Shubhra Aich, Eduardo R. Corral-Soto, Amir Nabatchian, Bingbing Liu
In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation.
no code implementations • 9 Feb 2021 • Linwei Ye, Mrigank Rochan, Zhi Liu, Xiaoqin Zhang, Yang Wang
In this paper, we propose a cross-modal self-attention (CMSA) module to utilize fine details of individual words and the input image or video, which effectively captures the long-range dependencies between linguistic and visual features.
Ranked #5 on Referring Expression Segmentation on J-HMDB (Precision@0.9 metric)
no code implementations • ICCV 2021 • Taivanbat Badamdorj, Mrigank Rochan, Yang Wang, Li Cheng
In video highlight detection, the goal is to identify the interesting moments within an unedited video.
1 code implementation • 23 Oct 2020 • Mahesh Kumar Krishna Reddy, Mrigank Rochan, Yiwei Lu, Yang Wang
In particular, we propose a new problem called unlabeled scene-adaptive crowd counting.
no code implementations • 31 Aug 2020 • Mrigank Rochan, Mahesh Kumar Krishna Reddy, Yang Wang
We consider the problem of sentence specified dynamic video thumbnail generation.
1 code implementation • ECCV 2020 • Mrigank Rochan, Mahesh Kumar Krishna Reddy, Linwei Ye, Yang Wang
In this paper, we propose a simple yet effective framework that learns to adapt highlight detection to a user by exploiting the user's history in the form of highlights that the user has previously created.
1 code implementation • 1 Feb 2020 • Mahesh Kumar Krishna Reddy, Mohammad Hossain, Mrigank Rochan, Yang Wang
We consider the problem of few-shot scene adaptive crowd counting.
1 code implementation • CVPR 2019 • Linwei Ye, Mrigank Rochan, Zhi Liu, Yang Wang
This module controls the information flow of features at different levels.
Ranked #14 on Referring Video Object Segmentation on Refer-YouTube-VOS (using extra training data)
no code implementations • 9 Apr 2019 • Tanzila Rahman, Mrigank Rochan, Yang Wang
A common approach for person re-identification is to first extract image features for all frames in the video, then aggregate all the features to form a video-level feature.
1 code implementation • 26 Oct 2018 • Shivansh Rao, Tanzila Rahman, Mrigank Rochan, Yang Wang
The goal is to identify a person from videos captured under different cameras.
no code implementations • 20 Jul 2018 • Seyed shahabeddin Nabavi, Mrigank Rochan, Yang, Wang
We propose a novel model that uses convolutional LSTM (ConvLSTM) to encode the spatiotemporal information of observed frames for future prediction.
no code implementations • 29 Jun 2018 • Md Amirul Islam, Mrigank Rochan, Shujon Naha, Neil D. B. Bruce, Yang Wang
In order to address this issue, we also propose Gated Feedback Refinement Network (G-FRNet) that addresses this limitation.
no code implementations • CVPR 2019 • Mrigank Rochan, Yang Wang
Our model aims to learn a mapping function $F : V \rightarrow S$ such that the distribution of resultant summary videos from $F(V)$ is similar to the distribution of $S$ with the help of an adversarial objective.
no code implementations • ECCV 2018 • Mrigank Rochan, Linwei Ye, Yang Wang
This paper addresses the problem of video summarization.
no code implementations • CVPR 2017 • Md Amirul Islam, Mrigank Rochan, Neil D. B. Bruce, Yang Wang
Effective integration of local and global contextual information is crucial for dense labeling problems.
no code implementations • 1 Mar 2017 • Md Amirul Islam, Shujon Naha, Mrigank Rochan, Neil Bruce, Yang Wang
We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at several resolutions.
no code implementations • CVPR 2015 • Mrigank Rochan, Yang Wang
We propose a method for transferring the appearance models of the familiar objects to the unseen object.