AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Game of Sketches: Deep Recurrent Models of Pictionary-Style Word Guessing

Ravi Kiran Sarvadevabhatla, Shiv Surya, Trisha Mittal, R. Venkatesh Babu

AAAI 2018 · Vision-language and multimodal › Visual question answering · approach: Visual reasoning diagnostics · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use a unified LSTM sequence model instead of the two-phase architecturePictionary-style word guessing · GuessWord-160 testaverage sequence-level accuracy (k=1): 46.33 -> 62.04Improved
Use a unified LSTM sequence model instead of the two-phase architecturePictionary-style word guessing · GuessWord-160 testaverage sequence-level accuracy (k=3): 52.08 -> 69.35Improved
Use a unified LSTM sequence model instead of the two-phase architecturePictionary-style word guessing · GuessWord-160 testaverage sequence-level accuracy (k=5): 54.46 -> 71.11Improved
Add recurrent temporal modeling to the CNN-only predictorM3 CNN sketch features · GuessWord-160 testaverage sequence-level accuracy (k=1): 43.61 -> 62.04Improved
Add recurrent temporal modeling to the CNN-only predictorM3 CNN sketch features · GuessWord-160 testaverage sequence-level accuracy (k=3): 51.54 -> 69.35Improved
Add recurrent temporal modeling to the CNN-only predictorM3 CNN sketch features · GuessWord-160 testaverage sequence-level accuracy (k=5): 54.18 -> 71.11Improved
Use 128 LSTM hidden units (ablation)Guess-word sequence model · GuessWord-160 validationaverage sequence-level accuracy (k=1): 52.77 -> 54.13Improved
Use 256 LSTM hidden units (ablation)Guess-word sequence model · GuessWord-160 validationaverage sequence-level accuracy (k=1): 52.77 -> 55.03Improved
Use 512 LSTM hidden units (ablation)Guess-word sequence model · GuessWord-160 validationaverage sequence-level accuracy (k=1): 52.77 -> 55.35Improved
Add 160-way auxiliary object classification to the Phase I CNN (ablation)Phase I transition predictor · GuessWord-160 testtransition location accuracy (window width 1): 17.37 -> 20.45Improved
Use transition-weighted sequence loss rather than default sequence loss (ablation)Phase I LSTM transition predictor · GuessWord-160 testtransition location accuracy (window width 3): 39.25 -> 41.48Improved
Use modified ranking loss rather than transition-weighted loss (ablation)Phase I LSTM transition predictor · GuessWord-160 testtransition location accuracy (window width 1): 19.20 -> 18.87Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy