Snap (United States)
In research, Snap (United States) stands highest in Computer Science (#302 of 4,667 worldwide) and Physical Sciences (#3,405 of 12,888 worldwide), 2022–2025. Relative to its size it is most specialised in Computer Vision and Pattern Recognition and Computer Science — Computer Vision and Pattern Recognition is 22.1× its share of world research.
- World rank, 2022–2025
- #6,089 of 28,054 · #13,217 all time
- Rank in United States
- #825 of 4,192
- Research works
- 206 ▲ 249% vs 2013–17
- Citations
- 9.3k 45.4 per fractional work
- Top-10% rate
- 37.2% record average 16.5%
- Open access
- 39% world 28%
What is Snap (United States) known for in research?
The fields where it stands highest, 2022–2025, ranked among every institution above the floor in each field.
| Field | World rank | Where that sits | Top-10% rate | Works | All time |
|---|---|---|---|---|---|
| Computer ScienceField | #302 of 4,667 | 39.7% | 69 | #1035 | |
| Physical SciencesDomain | #3,405 of 12,888 | 38.7% | 88 | #7761 |
Each strip is that field’s whole ranked pool, with the notch where Snap (United States) sits in it, in the colour of the band that rank falls in. The track under the rate is the rate itself: it carries no world mark, because the world rate differs by field (from about 6% to 21% in this record).
What does Snap (United States) specialise in?
Where its research is concentrated relative to its size: Computer Vision and Pattern Recognition takes 22.1× the share of its output that it takes of world research.
- Computer Vision and Pattern RecognitionSubfield · 28.9 works22×
- Computer ScienceField · 68.9 works8.5×
Location quotient, a volume reading rather than an impact one. It surfaces small, lopsided specialities.
Field profile
Location quotient across every field it publishes in: outside the ring is more than an institution of this size would be expected to publish, inside it is less.
Rings at 0.5×, 1× and 2×. Widest outward: Computer Science, 8.5×. Every wedge is a field page.
- Computer Science 8.5×
- Decision Sciences 1.8×
- Neuroscience 1.4×
- Mathematics 1.2×
- Physics and Astronomy 1.1×
- Engineering 0.9×
- Earth and Planetary Sciences 0.7×
- Psychology 0.5×
- Social Sciences 0.3×
- Health Professions 0.2×
- Arts and Humanities 0.2×
- Business, Management and Accounting 0.2×
- Economics, Econometrics and Finance 0.2×
- Biochemistry, Genetics and Molecular Biology 0.2×
- Agricultural and Biological Sciences 0.1×
- Medicine 0.1×
- Chemistry 0.1×
- Materials Science 0.0×
- Environmental Science 0.0×
Who are the top researchers at Snap (United States)?
Ranked on the composite score, Sergey Tulyakov, Menglei Chai and Neil Shah lead among researchers whose main affiliation is Snap (United States).
- 1 Sergey Tulyakov United States · #149,249 worldwide 354 citations · 58 works
- 2 Menglei Chai United States · #246,165 worldwide 106 citations · 21 works
- 3 Neil Shah United States · #312,468 worldwide 224 citations · 52 works
- 4 Linjie Yang United States · #357,685 worldwide 221 citations · 29 works
- 5 Maarten W. Bos United States · #389,800 worldwide 154 citations · 16 works
- 6 Aliaksandr Siarohin United States · #973,534 worldwide 93 citations · 27 works
- 7 Willi Menapace United States · #1,576,488 worldwide 20 citations · 16 works
Which keywords describe research at Snap (United States)?
By fractional works in 2022–2025, weighted toward what it does more of than the world: Deep Learning, Neural Networks, Unsupervised Learning, Representation Learning, Convolutional Networks, Generative Adversarial Networks, Machine Learning and Image Inpainting.
- Spatiotemporal Features
- Presence
- Sparse Representation
- Technology
- Applications
- Pose Estimation
- Graph Neural Networks
- Content-Based Retrieval
- Optical Flow
- Collaborative Filtering
- Depth Estimation
- Shape Representation
- Convolutional Neural Networks
- Virtual Reality
- Computer Graphics
- 3D Reconstruction
- Image Inpainting
- Convolutional Networks
- Unsupervised Learning
- Neural Networks
- Deep Learning
- Machine Learning
- Representation Learning
- Generative Adversarial Networks
- Image Synthesis
- Point Clouds
- Visualization
- Social Media
- Mesh Segmentation
- User Experience
- Semi-Supervised Learning
- Matrix Factorization
- Stereo Vision
- Graph Convolutional Networks
- Knowledge Graph Embedding
- Video Summarization
- Medical Imaging
- Social Interaction
- Embodiment
- Action Recognition
Size is fractional works in 2022–2025 in the topics tagged with each word; colour is the word's share of this institution's work against its share of the world's. The 40 words are chosen for being large and distinctive. Each links to the topic it comes from most.
All 40 words, with their numbers
- Deep Learning38▲ 11×43 topics
- Neural Networks17▲ 11×20 topics
- Machine Learning10▲ 3.1×29 topics
- Unsupervised Learning10▲ 66×3 topics
- Representation Learning9▲ 62×3 topics
- Convolutional Networks7▲ 50×3 topics
- Generative Adversarial Networks7▲ 86×2 topics
- Image Inpainting5▲ 127×1 topic
- Image Synthesis5▲ 127×1 topic
- 3D Reconstruction5▲ 54×2 topics
- Point Clouds5▲ 54×2 topics
- Computer Graphics5▲ 184×1 topic
- Visualization5▲ 85×1 topic
- Virtual Reality5▲ 9.0×6 topics
- Social Media4▲ 2.9×7 topics
- Convolutional Neural Networks4▲ 5.3×9 topics
- Mesh Segmentation4▲ 135×1 topic
- Shape Representation4▲ 135×1 topic
- User Experience4▲ 47×3 topics
- Depth Estimation4▲ 44×2 topics
- Semi-Supervised Learning4▲ 31×2 topics
- Collaborative Filtering4▲ 95×1 topic
- Matrix Factorization4▲ 95×1 topic
- Optical Flow4▲ 67×1 topic
- Stereo Vision4▲ 67×1 topic
- Content-Based Retrieval3▲ 110×1 topic
- Graph Convolutional Networks3▲ 24×2 topics
- Graph Neural Networks3▲ 57×1 topic
- Knowledge Graph Embedding3▲ 57×1 topic
- Pose Estimation3▲ 24×2 topics
- Video Summarization3▲ 110×1 topic
- Applications3▲ 9.3×1 topic
- Medical Imaging3▲ 5.1×4 topics
- Technology3▲ 4.8×1 topic
- Social Interaction2▲ 5.8×2 topics
- Sparse Representation2▲ 12×3 topics
- Embodiment2▲ 11×1 topic
- Presence2▲ 30×1 topic
- Action Recognition2▲ 38×1 topic
- Spatiotemporal Features2▲ 38×1 topic
Which research topics does Snap (United States) publish most on?
By volume in 2022–2025: Generative Adversarial Networks and Image Synthesis, Computer Graphics and Visualization Techniques, 3D Shape Modeling and Analysis and Recommender Systems and Techniques.
Area is fractional works; colour is the subfield each topic belongs to.
- 1 Generative Adversarial Networks and Image Synthesis Computer Vision and Pattern Recognition 5 works
- 2 Computer Graphics and Visualization Techniques Computer Graphics and Computer-Aided Design 5 works
- 3 3D Shape Modeling and Analysis Computational Mechanics 4 works
- 4 Recommender Systems and Techniques Information Systems 4 works
- 5 Advanced Vision and Imaging Computer Vision and Pattern Recognition 4 works
- 6 Video Analysis and Summarization Computer Vision and Pattern Recognition 3 works
- 7 Advanced Graph Neural Networks Artificial Intelligence 3 works
- 8 Augmented Reality Applications Computer Vision and Pattern Recognition 3 works
- 9 Virtual Reality Applications and Impacts Human-Computer Interaction 2 works
- 10 Human Pose and Action Recognition Computer Vision and Pattern Recognition 2 works
How open and international is its research?
Against the world’s own shares — the tick on each track. Both are shares of its output, so they sit on one scale and can be read against each other as well as against the world.
World: 28% of research is openly available.
World: 19% is written across borders.
How has Snap (United States)'s research output changed?
Output in 2018–2022 was 249% higher than in 2013–2017.
The same series as a ribbon — one cell per year, darker for more. The line above answers how much; this answers when.
Other research institutions in Los Angeles
- University of California, Los Angeles
- University of Southern California
- Cedars-Sinai Medical Center
- Film Independent
- UCLA Health
- Children's Hospital of Los Angeles
- California State University Los Angeles
- Loyola Marymount University
Research measures only: rankings here say nothing about teaching, admissions or student experience. Comparable institutions and collaboration partners are in the interactive view on the map.