5 citations · 11 across the 28 of their papers we have counts for
20 papers · 1 filter
Class Geometry as Supervision for Sample-Efficient Open-World Detection
Akash Rao, Zhou Chen, Revanth Reddy Palem +3
Open-world object detection requires models to recognize known categories, reject unfamiliar objects, and incorporate new classes over time. This is especially challenging in scarc…
CVT-Bench: Probing Spatial-State Integrity through Counterfactual Viewpoint Transformations
Shanmukha Vellamcheti, Uday Kiran Kothapalli, Disharee Bhowmick +1
Multimodal large language models (MLLMs) perform strongly on isolated spatial tasks, but whether their predictions remain persistent and mutually coherent across viewpoints and com…
Generalized Event Partonomy Inference with Structured Hierarchical Predictive Learning
Zhou Chen, Joe Lin, Sathyanarayanan N. Aakur\\
Humans naturally perceive continuous experience as a hierarchy of temporally nested events, fine-grained actions embedded within coarser routines. Replicating this structure in com…
FSP-DETR: Few-Shot Prototypical Parasitic Ova Detection
Shubham Trehan, Udhav Ramachandran, Akash Rao +2
Object detection in biomedical settings is fundamentally constrained by the scarcity of labeled data and the frequent emergence of novel or rare categories. We present FSP-DETR, a…
CRAFT: A Neuro-Symbolic Framework for Visual Functional Affordance Grounding
Zhou Chen, Joe Lin, Sathyanarayanan N. Aakur
We introduce CRAFT, a neuro-symbolic framework for interpretable affordance grounding, which identifies the objects in a scene that enable a given action (e.g., "cut"). CRAFT integ…
Hallucinate, Ground, Repeat: A Framework for Generalized Visual Relationship Detection
Shanmukha Vellamcheti, Sanjoy Kundu, Sathyanarayanan N. Aakur
Understanding relationships between objects is central to visual intelligence, with applications in embodied AI, assistive systems, and scene understanding. Yet, most visual relati…
A Probabilistic Jump-Diffusion Framework for Open-World Egocentric Activity Recognition
Sanjoy Kundu, Shanmukha Vellamcheti, Sathyanarayanan N. Aakur
Open-world egocentric activity recognition poses a fundamental challenge due to its unconstrained nature, requiring models to infer unseen activities from an expansive, partially o…
ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition
Sanjoy Kundu, Shanmukha Vellamcheti, Sathyanarayanan N. Aakur
Open-world egocentric activity recognition poses a fundamental challenge due to its unconstrained nature, requiring models to infer unseen activities from an expansive, partially o…
Self-supervised Multi-actor Social Activity Understanding in Streaming Videos
Shubham Trehan, Sathyanarayanan N. Aakur
This work addresses the problem of Social Activity Recognition (SAR), a critical component in real-world tasks like surveillance and assistive robotics. Unlike traditional event un…
ALGO: Object-Grounded Visual Commonsense Reasoning for Open-World Egocentric Action Recognition
Sanjoy Kundu, Shubham Trehan, Sathyanarayanan N. Aakur
Learning to infer labels in an open world, i.e., in an environment where the target "labels" are unknown, is an important characteristic for achieving autonomy. Foundation models p…
Shape-Graph Matching Network (SGM-net): Registration for Statistical Shape Analysis
Shenyuan Liang, Mauricio Pamplona Segundo, Sathyanarayanan N. Aakur +2
This paper focuses on the statistical analysis of shapes of data objects called shape graphs, a set of nodes connected by articulated curves with arbitrary shapes. A critical need…
Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning
Sanjoy Kundu, Shubham Trehan, Sathyanarayanan N. Aakur
Learning to infer labels in an open world, i.e., in an environment where the target ``labels'' are unknown, is an important characteristic for achieving autonomy. Foundation models…
Iterative Scene Graph Generation with Generative Transformers
Sanjoy Kundu, Sathyanarayanan N. Aakur
Scene graphs provide a rich, structured representation of a scene by encoding the entities (objects) and their spatial relationships in a graphical format. This representation has…
Towards Active Vision for Action Localization with Reactive Control and Predictive Learning
Shubham Trehan, Sathyanarayanan N. Aakur
Visual event perception tasks such as action localization have primarily focused on supervised learning settings under a static observer, i.e., the camera is static and cannot be c…
Actor-centered Representations for Action Localization in Streaming Videos
Sathyanarayanan N. Aakur, Sudeep Sarkar
Event perception tasks such as recognizing and localizing actions in streaming videos are essential for scaling to real-world application contexts. We tackle the problem of learnin…
Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision
Sathyanarayanan N. Aakur, Sanjoy Kundu, Nikhil Gunti
Advances in deep learning have enabled the development of models that have exhibited a remarkable tendency to recognize and even localize actions in videos. However, they tend to e…
Action Localization through Continual Predictive Learning
Sathyanarayanan N. Aakur, Sudeep Sarkar
The problem of action recognition involves locating the action in the video, both over time and spatially in the image. The dominant current approaches use supervised learning to s…
Unsupervised Gaze Prediction in Egocentric Videos by Energy-based Surprise Modeling
Sathyanarayanan N. Aakur, Arunkumar Bagavathi
Egocentric perception has grown rapidly with the advent of immersive computing devices. Human gaze prediction is an important problem in analyzing egocentric videos and has primari…
A Perceptual Prediction Framework for Self Supervised Event Segmentation
Sathyanarayanan N. Aakur, Sudeep Sarkar
Temporal segmentation of long videos is an important problem, that has largely been tackled through supervised learning, often requiring large amounts of annotated training data. I…
Going Deeper with Semantics: Video Activity Interpretation using Semantic Contextualization
Sathyanarayanan N. Aakur, Fillipe DM de Souza, Sudeep Sarkar
A deeper understanding of video activities extends beyond recognition of underlying concepts such as actions and objects: constructing deep semantic representations requires reason…