8 papers
VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cues
Sirnam Swetha, Rohit Gupta, Parth Parag Kulkarni +5
Video Question Answering (VideoQA) has made significant strides by leveraging multimodal learning to align visual and textual modalities. However, current benchmarks overwhelmingly…
TIGeR: A Unified Framework for Time, Images and Geo-location Retrieval
David G. Shatwell, Sirnam Swetha, Mubarak Shah
Many real-world applications in digital forensics, urban monitoring, and environmental analysis require jointly reasoning about visual appearance, location, and time. Beyond standa…
BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models
Vishal Narnaware, Ashmal Vayani, Rohit Gupta +2
Stereotype biases in Large Multimodal Models (LMMs) perpetuate harmful societal prejudices, undermining the fairness and equity of AI applications. As LMMs grow increasingly influe…
StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales
Nyle Siddiqui, Rohit Gupta, Sirnam Swetha +1
State space models (SSMs) have emerged as a competitive alternative to transformers in various tasks. Their linear complexity and hidden-state recurrence make them particularly att…
The Telephone Game: Evaluating Semantic Drift in Unified Models
Sabbir Mollah, Rohit Gupta, Sirnam Swetha +3
Employing a single, unified model (UM) for both visual understanding (image-to-text: I2T) and visual generation (text-to-image: T2I) has opened a new direction in Visual Language M…
Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety
Younggun Kim, Sirnam Swetha, Fazil Kagdi +1
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks. However, these models often infer and reveal sensitive biometric attrib…