ECCV 2020 accepted papers on Vision-language and multimodal
69 of the 1,358 papers accepted at ECCV 2020 (5.1%) are on Vision-language and multimodal, compared with 5.7% at ECCV 2018. They fall into 6 topics.
See ECCV 2020 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Human and embodied modeling · 33 papers
- UNITER: UNiversal Image-TExt Representation Learning (2,280 citations)
- SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization (341 citations)
- Image-based table recognition: data, model, and evaluation (332 citations)
- Improving One-stage Visual Grounding by Recursive Sub-query Construction (282 citations)
- ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language (266 citations)
- Captioning Images Taken by People Who Are Blind (204 citations)
- Linguistic Structure Guided Context Modeling for Referring Image Segmentation (201 citations)
- Consensus-Aware Visual-Semantic Embedding for Image-Text Matching (195 citations)
- RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition (194 citations)
- Contrastive Learning for Weakly Supervised Phrase Grounding (127 citations)
- Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models (112 citations)
- Grounded Situation Recognition (108 citations)
and 21 more in the interactive map.
Visual question answering · 12 papers
- Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision (117 citations)
- Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline (110 citations)
- Spatially Aware Multimodal Transformers for TextVQA (97 citations)
- Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder (85 citations)
- VQA-LOL: Visual Question Answering under the Lens of Logic (84 citations)
- Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering (56 citations)
- Visual Question Answering on Image Sets (29 citations)
- Multi-Agent Embodied Question Answering in Interactive Environments (27 citations)
- TRRNet: Tiered Relation Reasoning for Compositional Visual Question Answering (27 citations)
- Guessing State Tracking for Visual Dialogue (11 citations)
- Interpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision (11 citations)
- A Competence-aware Curriculum for Visual Concepts Learning via Question Answering
Cross-modal learning · 11 papers
- Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision (579 citations)
- SoundSpaces: Audio-Visual Navigation in 3D Environments (230 citations)
- Challenge-Aware RGBT Tracking (206 citations)
- Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing (166 citations)
- Multiple Sound Sources Localization from Coarse to Fine (163 citations)
- Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation (79 citations)
- Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition (47 citations)
- Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval (34 citations)
- Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model (20 citations)
- TPFN: Applying Outer Product along Time to Multimodal Sentiment Analysis Fusion on Incomplete Data (16 citations)
- Leveraging Acoustic Images for Effective Self-Supervised Audio Representation Learning (10 citations)
Multimodal LLMs · 5 papers
- Connecting Vision and Language with Localized Narratives (191 citations)
- VisualCOMET: Reasoning about the Dynamic Context of a Still Image (104 citations)
- VisualEchoes: Spatial Image Representation Learning through Echolocation (83 citations)
- A Closer Look at Generalisation in RAVEN (31 citations)
- Placepedia: Comprehensive Place Understanding with Multi-Faceted Annotations (8 citations)
Robot action and navigation · 5 papers
- Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments (334 citations)
- Improving Vision-and-Language Navigation with Image-Text Pairs from the Web (209 citations)
- Object-and-Action Aware Model for Visual Language Navigation (108 citations)
- Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler (82 citations)
- Active Visual Information Gathering for Vision-Language Navigation (77 citations)
CLIP and zero-shot · 3 papers
- Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks (1,806 citations)
- Learning Visual Representations with Caption Annotations (128 citations)
- Large-Scale Few-Shot Learning via Multi-Modal Knowledge Discovery (39 citations)
