TPAMI 2021 papers on Detection and segmentation
64 of the 516 papers published in TPAMI 2021 (12.4%) are on Detection and segmentation, compared with 10.3% at TPAMI 2020. They fall into 5 topics.
See TPAMI 2021 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
CNN features · 30 papers
- Salient Object Detection in the Deep Learning Era: An In-Depth Survey (869 citations)
- Learning to Match Anchors for Visual Object Detection (508 citations)
- CTNet: Context-Based Tandem Network for Semantic Segmentation (273 citations)
- Siamese Network for RGB-D Salient Object Detection and Beyond (252 citations)
- DeepGCNs: Making GCNs Go as Deep as CNNs (236 citations)
- AlignSeg: Feature-Aligned Segmentation Networks (190 citations)
- MobileSal: Extremely Efficient RGB-D Salient Object Detection (184 citations)
- From Handcrafted to Deep Features for Pedestrian Detection: A Survey (169 citations)
- Part-Object Relational Visual Saliency (168 citations)
- PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text (162 citations)
- ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting (159 citations)
- Re-thinking Co-Salient Object Detection (148 citations)
and 18 more in the interactive map.
Open-set and few-shot detection · 20 papers
- Image Segmentation Using Deep Learning: A Survey (4,212 citations)
- Concealed Object Detection (842 citations)
- Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (761 citations)
- DeepFake Detection Based on Discrepancies Between Faces and Their Context (388 citations)
- Segmenting Objects From Relational Visual Data (144 citations)
- Cascaded Parsing of Human-Object Interaction Recognition (121 citations)
- Instance-Invariant Domain Adaptive Object Detection via Progressive Disentanglement (121 citations)
- One Metric to Measure Them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks (50 citations)
- Class-Aware Sounding Objects Localization via Audiovisual Correspondence (47 citations)
- Self-Supervised Human Detection and Segmentation via Background Inpainting (22 citations)
- Texture Segmentation Benchmark (21 citations)
- Human-centric Relation Segmentation: Dataset and Solution (12 citations)
and 8 more in the interactive map.
Weakly supervised detection and segmentation · 8 papers
- Weakly Supervised Object Localization and Detection: A Survey (286 citations)
- Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation (162 citations)
- Online Attention Accumulation for Weakly Supervised Semantic Segmentation (81 citations)
- Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding (67 citations)
- TelecomNet: Tag-Based Weakly-Supervised Modally Cooperative Hashing Network for Image Retrieval (43 citations)
- Learning to Detect Salient Object with Multi-source Weak Supervision (22 citations)
- Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation (16 citations)
- Pyramidal Semantic Correspondence Networks (3 citations)
Tracking · 3 papers
- Detection and Tracking Meet Drones Challenge (1,587 citations)
- A Discriminative Single-Shot Segmentation Network for Visual Object Tracking (20 citations)
- Multi-Camera Trajectory Forecasting with Trajectory Tensors (15 citations)
