Visual Commonsense Reasoning Edit Task
Reasoning • Visual Reasoning
About
Benchmarks
Datasets
Greatest papers with code
Fusion of Detected Objects in Text for Visual Question Answering
IJCNLP 2019
• google-research/language
• 
To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language.
QUESTION ANSWERING VISUAL COMMONSENSE REASONING VISUAL QUESTION ANSWERING
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
ICLR 2020
• jackroos/VL-BERT
• 
We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short).
Ranked #1 on
Visual Question Answering
on VCR (QA-R) dev
LANGUAGE MODELLING QUESTION ANSWERING REFERRING EXPRESSION COMPREHENSION VISUAL COMMONSENSE REASONING VISUAL QUESTION ANSWERING
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
NeurIPS 2019
• facebookresearch/vilbert-multi-task
•
We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language.
IMAGE RETRIEVAL QUESTION ANSWERING VISUAL COMMONSENSE REASONING VISUAL GROUNDING VISUAL QUESTION ANSWERING
From Recognition to Cognition: Visual Commonsense Reasoning
CVPR 2019
• rowanz/r2c
•
While this task is easy for humans, it is tremendously difficult for today's vision systems, requiring higher-order cognition and commonsense reasoning about the world.
UNITER: UNiversal Image-TExt Representation Learning
ECCV 2020
• ChenRocks/UNITER
•
Different from previous work that applies joint random masking to both modalities, we use conditional masking on pre-training tasks (i. e., masked language/region modeling is conditioned on full observation of image/text).
Ranked #1 on
Visual Reasoning
on NLVR2 Test
LANGUAGE MODELLING QUESTION ANSWERING REFERRING EXPRESSION COMPREHENSION REPRESENTATION LEARNING TEXT MATCHING VISUAL COMMONSENSE REASONING VISUAL ENTAILMENT VISUAL QUESTION ANSWERING
Large-Scale Adversarial Training for Vision-and-Language Representation Learning
NeurIPS 2020
• zhegan27/VILLA
•
We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning.
QUESTION ANSWERING REFERRING EXPRESSION COMPREHENSION REPRESENTATION LEARNING VISUAL COMMONSENSE REASONING VISUAL ENTAILMENT VISUAL QUESTION ANSWERING
Heterogeneous Graph Learning for Visual Commonsense Reasoning
NeurIPS 2019
• yuweijiang/HGL-pytorch
•
Our HGL consists of a primal vision-to-answer heterogeneous graph (VAHG) module and a dual question-to-answer heterogeneous graph (QAHG) module to interactively refine reasoning paths for semantic agreement.
Unifying Vision-and-Language Tasks via Text Generation
On 7 popular vision-and-language benchmarks, including visual question answering, referring expression comprehension, visual commonsense reasoning, most of which have been previously modeled as discriminative tasks, our generative approach (with a single unified architecture) reaches comparable performance to recent task-specific state-of-the-art vision-and-language models.
CONDITIONAL TEXT GENERATION IMAGE CAPTIONING LANGUAGE MODELLING MULTI-TASK LEARNING QUESTION ANSWERING REFERRING EXPRESSION COMPREHENSION VISUAL COMMONSENSE REASONING VISUAL QUESTION ANSWERING
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
Natural language rationales could provide intuitive, higher-level explanations that are easily understandable by humans, complementing the more broadly studied lower-level explanations based on gradients or attention weights.
LANGUAGE MODELLING NATURAL LANGUAGE INFERENCE OBJECT RECOGNITION QUESTION ANSWERING VISUAL COMMONSENSE REASONING VISUAL QUESTION ANSWERING
Connective Cognition Network for Directional Visual Commonsense Reasoning
Inspired by this idea, towards VCR, we propose a connective cognition network (CCN) to dynamically reorganize the visual neuron connectivity that is contextualized by the meaning of questions and answers.