88 citations · 270 across the 23 of their papers we have counts for
20 papers · 1 filter
Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation
Tzu Ling Liu, Ian Stavness, Mrigank Rochan
Video Unsupervised Domain Adaptation (VUDA) poses a significant challenge in action recognition, requiring the adaptation of a model from a labeled source domain to an unlabeled ta…
Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality Hallucinations
Zahidul Islam, Sujoy Paul, Mrigank Rochan
Existing video highlight detection methods, although advanced, struggle to generalize well to all test videos. These methods typically employ a generic highlight detection model fo…
Unsupervised Video Highlight Detection by Learning from Audio and Visual Recurrence
Zahidul Islam, Sujoy Paul, Mrigank Rochan
With the exponential growth of video content, the need for automated video highlight detection to extract key moments or highlights from lengthy videos has become increasingly pres…
Improving LiDAR 3D Object Detection via Range-based Point Cloud Density Optimization
Eduardo R. Corral-Soto, Alaap Grandhi, Yannis Y. He +2
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 datase…
Domain Adaptation in 3D Object Detection with Gradual Batch Alternation Training
Mrigank Rochan, Xingxin Chen, Alaap Grandhi +2
We consider the problem of domain adaptation in LiDAR-based 3D object detection. Towards this, we propose a simple yet effective training strategy called Gradual Batch Alternation…
Domain Adaptation in LiDAR Semantic Segmentation via Alternating Skip Connections and Hybrid Learning
Eduardo R. Corral-Soto, Mrigank Rochan, Yannis Y. He +3
In this paper we address the challenging problem of domain adaptation in LiDAR semantic segmentation. We consider the setting where we have a fully-labeled data set from source dom…
Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters
Mrigank Rochan, Shubhra Aich, Eduardo R. Corral-Soto +2
In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant drop in performance o…
Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network
Linwei Ye, Mrigank Rochan, Zhi Liu +2
We consider the problem of referring segmentation in images and videos with natural language. Given an input image (or video) and a referring expression, the goal is to segment the…
AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
Mahesh Kumar Krishna Reddy, Mrigank Rochan, Yiwei Lu +1
We address the problem of image-based crowd counting. In particular, we propose a new problem called unlabeled scene-adaptive crowd counting. Given a new target scene, we would lik…
Sentence Guided Temporal Modulation for Dynamic Video Thumbnail Generation
Mrigank Rochan, Mahesh Kumar Krishna Reddy, Yang Wang
We consider the problem of sentence specified dynamic video thumbnail generation. Given an input video and a user query sentence, the goal is to generate a video thumbnail that not…
Adaptive Video Highlight Detection by Learning from User History
Mrigank Rochan, Mahesh Kumar Krishna Reddy, Linwei Ye +1
Recently, there is an increasing interest in highlight detection research where the goal is to create a short duration video from a longer video by extracting its interesting momen…
Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning
Mahesh Kumar Krishna Reddy, Mohammad Hossain, Mrigank Rochan +1
We consider the problem of few-shot scene adaptive crowd counting. Given a target camera scene, our goal is to adapt a model to this specific scene with only a few labeled images o…
Convolutional Temporal Attention Model for Video-based Person Re-identification
Tanzila Rahman, Mrigank Rochan, Yang Wang
The goal of video-based person re-identification is to match two input videos, so that the distance of the two videos is small if two videos contain the same person. A common appro…
Cross-Modal Self-Attention Network for Referring Image Segmentation
Linwei Ye, Mrigank Rochan, Zhi Liu +1
We consider the problem of referring image segmentation. Given an input image and a natural language expression, the goal is to segment the object referred by the language expressi…
Video-based Person Re-identification Using Spatial-Temporal Attention Networks
Shivansh Rao, Tanzila Rahman, Mrigank Rochan +1
We consider the problem of video-based person re-identification. The goal is to identify a person from videos captured under different cameras. In this paper, we propose an efficie…
Future Semantic Segmentation with Convolutional LSTM
Seyed shahabeddin Nabavi, Mrigank Rochan, Yang +1
We consider the problem of predicting semantic segmentation of future frames in a video. Given several observed frames in a video, our goal is to predict the semantic segmentation…
Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling
Md Amirul Islam, Mrigank Rochan, Shujon Naha +2
Effective integration of local and global contextual information is crucial for semantic segmentation and dense image labeling. We develop two encoder-decoder based deep learning a…
Video Summarization by Learning from Unpaired Data
Mrigank Rochan, Yang Wang
We consider the problem of video summarization. Given an input raw video, the goal is to select a small subset of key frames from the input video to create a shorter summary video…
Video Summarization Using Fully Convolutional Sequence Networks
Mrigank Rochan, Linwei Ye, Yang Wang
This paper addresses the problem of video summarization. Given an input video, the goal is to select a subset of the frames to create a summary video that optimally captures the im…
Label Refinement Network for Coarse-to-Fine Semantic Segmentation
Md Amirul Islam, Shujon Naha, Mrigank Rochan +2
We consider the problem of semantic image segmentation using deep convolutional neural networks. We propose a novel network architecture called the label refinement network that pr…