160 citations · 174 across the 19 of their papers we have counts for
21 papers
Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Vision-Language Models
Logan Mann, Yi Xia, Ajit Saravanan +6
Multimodal Foundation Models are increasingly used as reasoning agents, making reliability, knowing when a model may hallucinate, critical. A common intuition, which we call the At…
Where Reliability Lives in Vision-Language Models: A Mechanistic Study of Attention, Hidden States, and Causal Circuits
Logan Mann, Ajit Saravanan, Ishan Dave +4
A pervasive intuition holds that vision-language models (VLMs) are most trustworthy when their attention maps look sharp: concentrated attention on the queried region should imply…
Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding
Joseph Fioresi, Ishan Rajendrakumar Dave, Mubarak Shah
We introduce a novel formulation of visual privacy preservation for video foundation models that operates entirely in the latent space. While spatio-temporal features learned by fo…
GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space
David G. Shatwell, Ishan Rajendrakumar Dave, Sirnam Swetha +1
Timestamp prediction aims to determine when an image was captured using only visual information, supporting applications such as metadata correction, retrieval, and digital forensi…
From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos
Animesh Gupta, Jay Parmar, Ishan Rajendrakumar Dave +1
Composed Video Retrieval (CoVR) retrieves a target video given a query video and a modification text describing the intended change. Existing CoVR benchmarks emphasize appearance s…
ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
Joseph Fioresi, Ishan Rajendrakumar Dave, Mubarak Shah
Bias in machine learning models can lead to unfair decision making, and while it has been well-studied in the image and text domains, it remains underexplored in action recognition…
FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition
Ishan Rajendrakumar Dave, Mamshad Nayeem Rizve, Mubarak Shah
Real-life applications of action recognition often require a fine-grained understanding of subtle movements, e.g., in sports analytics, user interactions in AR/VR, and surgical vid…
Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets
Ishan Rajendrakumar Dave, Fabian Caba Heilbron, Mubarak Shah +1
Temporal video alignment aims to synchronize the key events like object interactions or action phase transitions in two videos. Such methods could benefit various video editing, pr…
CodaMal: Contrastive Domain Adaptation for Malaria Detection in Low-Cost Microscopes
Ishan Rajendrakumar Dave, Tristan de Blegiers, Chen Chen +1
Malaria is a major health issue worldwide, and its diagnosis requires scalable solutions that can work effectively with low-cost microscopes (LCM). Deep learning-based methods have…
No More Shortcuts: Realizing the Potential of Temporal Self-Supervision
Ishan Rajendrakumar Dave, Simon Jenni, Mubarak Shah
Self-supervised approaches for video have shown impressive results in video understanding tasks. However, unlike early works that leverage temporal self-supervision, current state-…
Egocentric RGB+Depth Action Recognition in Industry-Like Settings
Jyoti Kini, Sarah Fleischer, Ishan Dave +1
Action recognition from an egocentric viewpoint is a crucial perception task in robotics and enables a wide range of human-robot interactions. While most computer vision approaches…
Ensemble Modeling for Multimodal Visual Action Recognition
Jyoti Kini, Sarah Fleischer, Ishan Dave +1
In this work, we propose an ensemble modeling approach for multimodal action recognition. We independently train individual modality models using a variant of focal loss tailored t…
EventTransAct: A video transformer-based framework for Event-camera based action recognition
Tristan de Blegiers, Ishan Rajendrakumar Dave, Adeel Yousaf +1
Recognizing and comprehending human actions and gestures is a crucial perception requirement for robots to interact with humans and carry out tasks in diverse domains, including se…
TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection
Joseph Fioresi, Ishan Rajendrakumar Dave, Mubarak Shah
Video anomaly detection (VAD) without human monitoring is a complex computer vision task that can have a positive impact on society if implemented successfully. While recent advanc…
TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition
Ishan Rajendrakumar Dave, Mamshad Nayeem Rizve, Chen Chen +1
Semi-Supervised Learning can be more beneficial for the video domain compared to images because of its higher annotation cost and dimensionality. Besides, any video understanding t…
TransVisDrone: Spatio-Temporal Transformer for Vision-based Drone-to-Drone Detection in Aerial Videos
Tushar Sangam, Ishan Rajendrakumar Dave, Waqas Sultani +1
Drone-to-drone detection using visual feed has crucial applications, such as detecting drone collisions, detecting drone attacks, or coordinating flight with other drones. However,…
SPAct: Self-supervised Privacy Preservation for Action Recognition
Ishan Rajendrakumar Dave, Chen Chen, Mubarak Shah
Visual private information leakage is an emerging key issue for the fast growing applications of video understanding like activity recognition. Existing approaches for mitigating p…
Baba is Y'all 2.0: Design and Investigation of a Collaborative Mixed-Initiative System
M Charity, Isha Dave, Ahmed Khalifa +1
This paper describes a new version of the mixed-initiative collaborative level designing system: Baba is Y'all, as well as the results of a user study on the system. Baba is Y'all…
"Knights": First Place Submission for VIPriors21 Action Recognition Challenge at ICCV 2021
Ishan Dave, Naman Biyani, Brandon Clark +3
This technical report presents our approach "Knights" to solve the action recognition task on a small subset of Kinetics-400 i.e. Kinetics400ViPriors without using any extra-data.…
TCLR: Temporal Contrastive Learning for Video Representation
Ishan Dave, Rohit Gupta, Mamshad Nayeem Rizve +1
Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work…
Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos
Mamshad Nayeem Rizve, Ugur Demir, Praveen Tirupattur +5
Activity detection in security videos is a difficult problem due to multiple factors such as large field of view, presence of multiple activities, varying scales and viewpoints, an…