activity
20172023
most citedMultiscale Vision Transformers

56 citations · 101 across the 5 of their papers we have counts for

collaborators

9 papers

cs.LG2023

PaReprop: Fast Parallelized Reversible Backpropagation

Tyler Zhu, Karttikeya Mangalam

The growing size of datasets and deep learning models has made faster and memory-efficient training crucial. Reversible transformers have recently been introduced as an exciting ne…

cs.CV2021

LOKI: Long Term and Key Intentions for Trajectory Prediction

Harshayu Girase, Haiming Gang, Srikanth Malla +4

Recent advances in trajectory prediction have shown that explicit reasoning about agents' intent is important to accurately forecast their motion. However, the current research act…

cs.CV202156 cited

Multiscale Vision Transformers

Haoqi Fan, Bo Xiong, Karttikeya Mangalam +4

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multisca…

cs.CV202037 cited

From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting

Karttikeya Mangalam, Yang An, Harshayu Girase +1

Human trajectory forecasting is an inherently multi-modal problem. Uncertainty in future trajectories stems from two sources: (a) sources that are known to the agent but unknown to…

cs.CV20208 cited

Long-term Human Motion Prediction with Scene Context

Zhe Cao, Hang Gao, Karttikeya Mangalam +3

Human movement is goal-directed and influenced by the spatial layout of the objects in the scene. To plan future human motion, it is crucial to perceive the environment -- imagine…

cs.CV2020

It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction

Karttikeya Mangalam, Harshayu Girase, Shreyas Agarwal +4

Human trajectory forecasting with multiple socially interacting agents is of critical importance for autonomous navigation in human environments, e.g., for self-driving cars and so…