Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR
Visual Commonsense Reasoning (VCR) calls for explanatory reasoning behind question
answering over visual scenes. To achieve this goal, a model is required to provide an …
answering over visual scenes. To achieve this goal, a model is required to provide an …
Learning Feature Semantic Matching for Spatio-Temporal Video Grounding
Spatio-temporal video grounding (STVG) aims to localize a spatio-temporal tube, including
temporal boundaries and object bounding boxes, that semantically corresponds to a given …
temporal boundaries and object bounding boxes, that semantically corresponds to a given …
Two-Step Discrete Hashing for Cross-Modal Retrieval
Cross-modal hashing is an effective approach for information retrieval from large and
heterogeneous cross-modal datasets, owing to its low storage cost and high computational …
heterogeneous cross-modal datasets, owing to its low storage cost and high computational …
Unbiased Visual Question Answering by Leveraging Instrumental Variable
Y Pan, J Liu, L Jin, Z Li - IEEE Transactions on Multimedia, 2024 - ieeexplore.ieee.org
Existing unbiased visual question answering (VQA) models reduce the spurious correlation
between questions and answers to force the models to focus on visual information …
between questions and answers to force the models to focus on visual information …
How to Use Language Expert to Assist Inference for Visual Commonsense Reasoning
Visual Commonsense Reasoning (VCR) task requires Vision and Language Model (VLM) to
capture cognitive level clues from the visual-language input and give the right answers to …
capture cognitive level clues from the visual-language input and give the right answers to …
Multi-modal Large Language Model Enhanced Pseudo 3D Perception Framework for Visual Commonsense Reasoning
The visual commonsense reasoning (VCR) task is to choose an answer and provide a
justifying rationale based on the given image and textural question. Representative works …
justifying rationale based on the given image and textural question. Representative works …
[PDF][PDF] Multi-task Visual Semantic Embedding Network for image-text retrieval
Image-text retrieval aims to capture the semantic correspondence between images and
texts, which serves as a foundation and crucial component in multi-modal recommendations …
texts, which serves as a foundation and crucial component in multi-modal recommendations …