关注
Kumara Kahatapitiya
Kumara Kahatapitiya
PhD candidate, Stony Brook University
在 cs.stonybrook.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
R Dai, S Das, K Kahatapitiya, MS Ryoo, F Bremond
CVPR 2022, 2022
672022
Coarse-Fine Networks for Temporal Activity Detection in Videos
K Kahatapitiya, MS Ryoo
CVPR 2021, 2021
412021
Swift: Adaptive Video Streaming with Layered Neural Codecs
M Dasari, K Kahatapitiya, SR Das, A Balasubramanian, D Samaras
NSDI 2022, 2022
332022
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
J Shang, K Kahatapitiya, X Li, MS Ryoo
ECCV 2022, 2022
27*2022
Exploiting the Redundancy in Convolutional Filters for Parameter Reduction
K Kahatapitiya, R Rodrigo
WACV 2021, 2021
192021
Token Turing Machines
MS Ryoo, K Gopalakrishnan, K Kahatapitiya, T Xiao, K Rao, A Stone, Y Lu, ...
CVPR 2023, 2023
142023
Feature-Dependent Cross-Connections in Multi-Path Neural Networks
D Tissera, K Vithanage, R Wijesinghe, K Kahatapitiya, S Fernando, ...
ICPR 2020, 2021
12*2021
Weakly-guided Self-supervised Pretraining for Temporal Activity Detection
K Kahatapitiya, Z Ren, H Li, Z Wu, G Hua, MS Ryoo
AAAI 2023, 2023
102023
VicTR: Video-conditioned Text Representations for Activity Recognition
K Kahatapitiya, A Arnab, A Nagrani, MS Ryoo
CVPR 2024, 2024
82024
SWAT: Spatial Structure Within and Among Tokens
K Kahatapitiya, MS Ryoo
IJCAI 2023, 2023
72023
StARformer: Transformer with State-Action-Reward Representations for Robot Learning
J Shang, X Li, K Kahatapitiya, YC Lee, MS Ryoo
T-PAMI, 2022
72022
Context-Aware Automatic Occlusion Removal
K Kahatapitiya, D Tissera, R Rodrigo
ICIP 2019, 2019
72019
Language Repository for Long Video Understanding
K Kahatapitiya, K Ranasinghe, J Park, MS Ryoo
arXiv preprint arXiv:2403.14622, 2024
52024
Foxtail+: A Learning with Errors-based Authentication Protocol for Resource-Constrained Devices
M Monteiro, K Kahatapitiya, HJ Asghar, K Thilakarathna, T Rakotoarivelo, ...
Cryptology ePrint Archive, 2020
32020
Object-Centric Diffusion for Efficient Video Editing
K Kahatapitiya, A Karjauv, D Abati, F Porikli, YM Asano, A Habibian
ECCV 2024, 2024
22024
Low-power Step Counting Paired with Electromagnetic Energy Harvesting for Wearables
K Kahatapitiya, C Weerasinghe, J Jayawardhana, H Kuruppu, ...
ISWC 2018, 2018
22018
Understanding Long Videos in One Multimodal Language Model Pass
K Ranasinghe, X Li, K Kahatapitiya, MS Ryoo
arXiv preprint arXiv:2403.16998, 2024
12024
On the Exact Outage Probability of 2×2 MIMO-MRC in Correlated Rician Fading
P Dharmawansa, K Kahatapitiya, S Atapattu, C Tellambura
WCNC 2020, 2020
1*2020
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
X Li, C Mata, J Park, K Kahatapitiya, YS Jang, J Shang, K Ranasinghe, ...
arXiv preprint arXiv:2406.20095, 2024
2024
Too many frames, not all useful: Efficient Strategies for Long-form Video QA
J Park, K Ranasinghe, K Kahatapitiya, W Ryoo, D Kim, MS Ryoo
arXiv e-prints, arXiv: 2406.09396, 2024
2024
系统目前无法执行此操作,请稍后再试。
文章 1–20