Mohsen Malmir

Mohsen Malmir

Auto-generated profile, based on publicly available information

Mohsen Malmir

Meta, New York, NY, USA

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2017 in Computer Vision and Image Understanding
Verified
Journal Article
Closed access
MMMohsen Malmir
Mohsen Malmir
KSKaran Sikka
Karan Sikka
DFDeborah Forster
Deborah Forster
IFIan Fasel
Ian Fasel
JMJavier R. Movellan
Javier R. Movellan
GCGarrison W. Cottrell
Garrison W. Cottrell

1 March 2021 in Journal of Experimental Child Psychology
Verified
Journal Article
Closed access
KSKristyn Sommer
Kristyn Sommer
VSVirginia Slaughter
Virginia Slaughter
JWJanet Wiles
Janet Wiles
KOKathryn Owen
Kathryn Owen
ACAndrea A. Chiba
Andrea A. Chiba
MNMark Nielsen
Mark Nielsen

1 September 2017
Verified
Conference Paper
Closed access
MMMohsen Malmir
Mohsen Malmir
GCGarrison W. Cottrell
Garrison W. Cottrell
Active Object Recognition (AOR) has been approached as an unsupervised learning problem, in which optimal trajectories for object inspection are not known and to be discovered by reducing label uncertainty or training with reinforcement learning. Such approaches suffer from local optima and have no guarantees of the quality of their solution. In this paper, we treat AOR as a Partially Observable Markov Decision Process (POMDP) and find near-optimal values and corresponding action-values of training data using Belief Tree Search (BTS) on the AOR belief Markov Decision Process (MDP). AOR then reduces to the problem of knowledge transfer from these action-values to the test set. We train a Long Short Term Memory (LSTM) network on these values to predict the best next action on the training set rollouts and experimentally show that our method generalizes well to explore novel objects and novel views of familiar objects with high accuracy. We compare this supervised scheme against guided policy search, and show that the LSTM network reaches higher recognition accuracy compared to the guided policy search and guided Neurally Fitted Q-iteration. We further look into optimizing the observation function to increase the total collected reward during active recognition. In AOR, the observation function is known only approximately. We derive a gradient-based update for the observation function to increase the total expected reward. We show that by optimizing the observation function and retraining the supervised LSTM network, the AOR performance on the test set improves significantly.

22 September 2025
Verified
Conference Paper
Open access
MBMahanth Kumar Beeraka
Mahanth Kumar Beeraka
CCChen Chen
Chen Chen
YLYining Lu
Yining Lu
BMBriac Marcatte
Briac Marcatte
WLWeikun Lyu
Weikun Lyu
YLYang Li
Yang Li

27 September 2026
Verified
Conference Paper
Open access
MMMohsen Malmir
Mohsen Malmir
HNHoussam Nassif
Houssam Nassif
DSDanish Nasir Shaikh
Danish Nasir Shaikh
TRTaher Rahgooy
Taher Rahgooy
MBMurat Bayir
Murat Bayir