Visual Commonsense Reasoning
29 papers with code • 7 benchmarks • 7 datasets
Image source: Visual Commonsense Reasoning
Benchmarks
These leaderboards are used to track progress in Visual Commonsense Reasoning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
VCR
ScienceQA
IconQA
GD-VCR
WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images
QLEVR
Visual Commonsense Immorality benchmark
Most implemented papers
Heterogeneous Graph Learning for Visual Commonsense Reasoning
yuweijiang/HGL-pytorch
•
•
NeurIPS 2019
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.
TAB-VCR: Tags and Attributes based Visual Commonsense Reasoning Baselines
Deanplayerljx/tab-vcr
•
•
NeurIPS 2019
Despite impressive recent progress that has been reported on tasks that necessitate reasoning, such as visual question answering and visual dialog, models often exploit biases in datasets.
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.
TAB-VCR: Tags and Attributes based VCR Baselines
Deanplayerljx/tab-vcr
•
•
NeurIPS 2019
Despite impressive recent progress that has been reported on tasks that necessitate reasoning, such as visual question answering and visual dialog, models often exploit biases in datasets.
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
allenai/visual-reasoning-rationalization
•
•
Findings of the Association for Computational Linguistics 2020
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.
MERLOT: Multimodal Neural Script Knowledge Models
rowanz/merlot
•
•
NeurIPS 2021
As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future.
Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory
tanjatang/DMVCR
•
•
Moreover, the proposed model provides intuitive interpretation into visual commonsense reasoning.
Interpretable Visual Understanding with Cognitive Attention Network
tanjatang/CAN
•
•
While image understanding on recognition-level has achieved remarkable advancements, reliable visual scene understanding requires comprehensive image understanding on recognition-level but also cognition-level, which calls for exploiting the multi-source information as well as learning different levels of understanding and extensive commonsense knowledge.
Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning
wadeyin9712/gd-vcr
•
•
EMNLP 2021
Commonsense is defined as the knowledge that is shared by everyone.
Towards artificial general intelligence via a multimodal foundation model
To overcome this limitation and take a solid step towards artificial general intelligence (AGI), we develop a foundation model pre-trained with huge multimodal data, which can be quickly adapted for various downstream cognitive tasks.
