ECCV 2018 accepted papers on Vision-language and multimodal
44 of the 776 papers accepted at ECCV 2018 (5.7%) are on Vision-language and multimodal, compared with 4.3% at ECCV 2016. They fall into 6 topics.
See ECCV 2018 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
Visual question answering · 15 papers
- A Joint Sequence Fusion Model for Video Question Answering and Retrieval (358 citations)
- Visual Coreference Resolution in Visual Dialog using Neural Module Networks (159 citations)
- Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering (107 citations)
- Learning Visual Question Answering by Bootstrapping Hard Attention (102 citations)
- VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions (96 citations)
- Question-Guided Hybrid Convolution for Visual Question Answering (79 citations)
- Multimodal Dual Attention Memory for Video Story Question Answering (77 citations)
- Deep Attention Neural Tensor Network for Visual Question Answering (68 citations)
- ADVISE: Symbolism and External Knowledge for Decoding Advertisements (59 citations)
- Question Type Guided Attention in Visual Question Answering (55 citations)
- A Dataset and Architecture for Visual Reasoning with a Working Memory (48 citations)
- Visual Question Answering as a Meta Learning Task (44 citations)
and 3 more in the interactive map.
Human and embodied modeling · 15 papers
- Unified Perceptual Parsing for Scene Understanding (2,344 citations)
- Stacked Cross Attention for Image-Text Matching (1,435 citations)
- Women also Snowboard: Overcoming Bias in Captioning Models (415 citations)
- Recurrent Fusion Network for Image captioning (306 citations)
- Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data (143 citations)
- Conditional Image-Text Embedding Networks (123 citations)
- Unpaired Image Captioning by Language Pivoting (93 citations)
- ``Factual'' or ``Emotional'': Stylized Image Captioning with Adaptive Learning and Attention (92 citations)
- Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias (88 citations)
- Boosted Attention: Leveraging Human Attention for Image Captioning (53 citations)
- Single Shot Scene Text Retrieval (49 citations)
- Robust fitting in computer vision: easy or hard? (48 citations)
and 3 more in the interactive map.
Cross-modal learning · 11 papers
- Audio-Visual Scene Analysis with Self-Supervised Multisensory Features (722 citations)
- Audio-Visual Event Localization in Unconstrained Videos (541 citations)
- Deep Cross-Modal Projection Learning for Image-Text Matching (520 citations)
- Learning Deep Representations with Probabilistic Knowledge Transfer (498 citations)
- Objects that Sound (452 citations)
- The Sound of Pixels (445 citations)
- Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input (177 citations)
- Cross-Modal Ranking with Soft Consistency and Noisy Labels for Robust RGB-T Tracking (162 citations)
- Learnable PINs: Cross-Modal Embeddings for Person Identity (157 citations)
- Cross-Modal Hamming Hashing (153 citations)
- Attention-aware Deep Adversarial Hashing for Cross-Modal Retrieval (140 citations)
Robot action and navigation · 1 paper
Multimodal LLMs · 1 paper
- On Offline Evaluation of Vision-based Driving Models (103 citations)
