activity
20142024
most citedDiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization

7 citations · 15 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV2024

Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos

Shakeeb Murtaza, Marco Pedersoli, Aydin Sarraf +1

Weakly-Supervised Video Object Localization (WSVOL) involves localizing an object in videos using only video-level labels, also referred to as tags. State-of-the-art WSVOL methods…

cs.CV2023★ 7 cited

DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization

Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli +2

Self-supervised vision transformers (SSTs) have shown great potential to yield rich localization maps that highlight different objects in an image. However, these maps remain class…

cs.CV2022★ 5 cited

Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization

Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli +2

Self-supervised vision transformers can generate accurate localization maps of the objects in an image. However, since they decompose the scene into multiple maps containing variou…

cs.CV2022★ 1 cited

Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization

Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli +2

Drones are employed in a growing number of visual recognition applications. A recent development in cell tower inspection is drone-based asset surveillance, where the autonomous fl…

cs.CV2021

F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling

Soufiane Belharbi, Aydin Sarraf, Marco Pedersoli +3

Class Activation Mapping (CAM) methods have recently gained much attention for weakly-supervised object localization (WSOL) tasks. They allow for CNN visualization and interpretati…

cs.MA2021★ 1 cited

Intelligent Link Adaptation for Grant-Free Access Cellular Networks: A Distributed Deep Reinforcement Learning Approach

Joao V. C. Evangelista, Zeeshan Sattar, Georges Kaddoum +2

With the continuous growth of machine-type devices (MTDs), it is expected that massive machine-type communication (mMTC) will be the dominant form of traffic in future wireless net…

math.PR2015

On the Riemann-Hilbert factorization problem for positive definite functions

Dan Kucerovsky, Amir T. P. Najafabadi, Aydin Sarraf

We give several general theorems concerning positive definite solutions of Riemann-Hilbert problems on the real line. Furthermore, as an example, we apply our theory to the charact…

math.OA2014★ 1 cited

Schur Multipliers and Matrix Products

Dan Kucerovsky, Aydin Sarraf

We give necessary and sufficient conditions for a Schur map to be a homomorphism, with some generalizations to the infinite-dimensional case. In the finite-dimensional case, we fin…