The DOI matches its Crossref record; 36 of the 37 references it cites were found in a registry or an index.
Direct face detection and video reconstruction from event cameras
Abstract
Event cameras are emerging as a new class of cameras, to potentially rival conventional CMOS cameras, because of their high speed operation and low power consumption. Pixels in an event camera operate in parallel and fire asynchronous spikes when individual pixels encounter a change in intensity that is greater than a pre-determined threshold. Such event-based cameras have an immense potential in battery-operated or always-on application scenarios, owing to their low power consumption. These event-based cameras can be used for direct detection from event streams, and we demonstrate this potential using face detection as an example application. We first propose and develop a patch-based model for the event streams acquired from such cameras. We demonstrate the utility and robustness of the patch-based model for event-based video reconstruction and event-based direct face detection. We are able to reconstruct images and videos at over 2,000 fps from the acquired event streams. In addition, we demonstrate the first direct face detection from event streams, highlighting the potential of these event-based cameras for power-efficient vision applications.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Recently, deep neural network-based event-to-image conversion models [8]-[11] have demonstrated impressive abilities in recovering gray-scale images from event streams, posing a potential risk to the privacy aspect of event-based vision applications.”
From Event Anonymization: Privacy-Preserving Person Re-Identification and Pose Estimation in Event-Based Vision (2024) · cites this paper as [36]
Citations
Cites
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097
$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
Aharon, M., Elad, M., & Bruckstein, A. M. (2006) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2006.881199 · Cited by 9,464
Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937655 · Cited by 8,216
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
Elad, M., & Aharon, M. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881969 · Cited by 5,321
Image Super-Resolution Via Sparse Representation
Yang, J., Wright, J. N., Huang, T. S., & Ma, Y. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2050625 · Cited by 5,241
Pati, Y., Rezaiifar, R., & Krishnaprasad, P. (1993) · Proceedings of 27th Asilomar Conference on Signals, Systems and Computers · doi:10.1109/acssc.1993.342465 · Cited by 4,928
A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision Sensor
Lichtsteiner, P., Posch, C., & Delbruck, T. (2008) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2007.914337 · Cited by 2,485 · cited 13×
“Data Finally, we conduct face detection experiments using real event streams from the DVS128.”
BackgroundMethodInfluentialFace detection, pose estimation, and landmark localization in the wild
Zhu, X., & Ramanan, D. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6248014 · Cited by 2,171
Research works printed but not linked: 3
- Grasshopper3 4.1 mp mono usb3 vision (cmosis cmv40003e5)
- 10.1016/j.neunet.2013.03.006 · DOI
- 2014, MATLAB. version 8.3 (R2014a)
Cited by
Sorted by citations
Gallego, G., Delbruck, T., Orchard, G., Bartolozzi, C., Taba, B., Censi, A., Leutenegger, S., Davison, A. J., Conradt, J., Daniilidis, K., et al. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3008413 · Cited by 2,566
Gallego, G., Delbrück, T., Orchard, G., Bartolozzi, C., Taba, B., Censi, A., Leutenegger, S., Davison, A. J., Conradt, J., Daniilidis, K., et al. (2020) · Zurich Open Repository and Archive (University of Zurich) · doi:10.3929/ethz-b-000521357 · Cited by 590
Events-To-Video: Bringing Modern Computer Vision to Event Cameras
Rebecq, H., Ranftl, R., Koltun, V., & Scaramuzza, D. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00398 · Cited by 462
“contrast to [4], we do not reconstruct individual intensity images from small windows of events, but instead reconstruct a temporally consistent video from a long stream of events (several seconds) using a recurrent network.”
BackgroundBringing a Blurry Frame Alive at High Frame-Rate With an Event Camera
Pan, L., Scheerlinck, C., Yu, X., Hartley, R. I., Liu, M., & Dai, Y. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00698 · Cited by 318
“The existing methods can be in general categorized as 1) Event data only solutions [1, 27, 2], where the results tend to lack the texture and consistency of natural videos, as they fail to use the complementary information contained in the low frame-rate intensity image; 2) Low framerate intensity-image-only solutions…”
MethodFast Image Reconstruction with an Event Camera
Scheerlinck, C., Rebecq, H., Gehrig, D., Barnes, N. M., Mahony, R. E., & Scaramuzza, D. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093366 · Cited by 252
“[4], who used a simulator to learn a sparse patch-based dictionary to match event patches to gradient patches.”
Wang, L., Mostafavi, M., Ho, Y.-S., & Yoon, K.-J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.01032 · Cited by 240
“In [3], intensity images were reconstructed using a patch-based sparse dictionary both on simulated and real event data in the presence of noise.”
MethodContinuous-Time Intensity Estimation Using Event Cameras
Scheerlinck, C., Barnes, N. M., & Mahony, R. E. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20873-8_20 · Cited by 236
Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation
Munda, G., Reinbacher, C., & Pock, T. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1106-2 · Cited by 181
“[2] use a dictionary learning approach to map the sparse, accumulated event information to infer image gradients.”
MethodLearning Event-Driven Video Deblurring and Interpolation
Lin, S., Zhang, J., Pan, J., Jiang, Z., Zou, D., Wang, Y., Chen, J., & Ren, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58598-3_41 · Cited by 146
“Significant efforts [3,2,15,21] have been devoted to [9].”
BackgroundEvent Enhanced High-Quality Image Recovery
Wang, B., He, J., Yu, L., Xia, G.-S., & Yang, W. T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58601-0_10 · Cited by 139
Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging
Wang, Z. W., Duan, P., Cossairt, O. S., Katsaggelos, A. K., Huang, T., & Shi, B. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00168 · Cited by 104
“Figure 11: HDR image reconstruction based on Poission method in [3].”
MethodBaldwin, R. W., Almatrafi, M., Asari, V. K., & Hirakawa, K. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00177 · Cited by 106
CED: Color Event Camera Dataset
Scheerlinck, C., Rebecq, H., Stoffregen, T., Barnes, N. M., Mahony, R. E., & Scaramuzza, D. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00215
“They have been used in feature detection and tracking [3–6], depth estimation [7–10], stereo [11–14], optical flow [15–18], image reconstruction [19–25], localization [26–29], SLAM [30–32], visualinertial odometry [33–36], pattern recognition [37–40], and more.”
BackgroundMethodHigh Frame Rate Video Reconstruction based on an Event Camera
Pan, L., Hartley, R., Scheerlinck, C., Liu, M., Yu, X., & Dai, Y. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3036667 · Cited by 99
“Barua et al. [9] generate image gradients by dictionary learning and obtain a logarithmic intensity image via Poisson reconstruction.”
BackgroundMethodEvent Cameras in Automotive Sensing: A Review
Shariff, W., Dilmaghani, M. S., Kielty, P., Moustafa, M., Lemley, J., & Corcoran, P. (2024) · IEEE Access · doi:10.1109/access.2024.3386032 · Cited by 92
Learning to Reconstruct HDR Images from Events, with Applications to Depth and Flow Prediction
Mostafavi, M., Wang, L., & Yoon, K. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01410-2 · Cited by 72
“2008), or patch-based sparse dictionaries (Barua et al. 2016).”
BackgroundComputational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision
Suo, J., Zhang, W., Gong, J., Yuan, X., Brady, D. J., & Dai, Q. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3338272 · Cited by 74
“By directly performing detection from the event streams [502], such sensing mechanism obtains qualitative improvement in both perception speed and sensitivity [503], [504], especially under low-light conditions.”
BackgroundChen, H., Jayasuriya, S., Yang, J., Stephen, J., Sivaramakrishnan, S., Veeraraghavan, A., & Molnar, A. C. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.104 · Cited by 66
“Dynamic Vision Sensors (DVS) have been used for face recognition while saving energy compared to conventional image sensors [34].”
MethodSelf-citationLearning to See in the Dark with Events
Zhang, S., Zhang, Y., Jiang, Z., Zou, D., Ren, J., & Zhou, B. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58523-5_39 · Cited by 66
“Barua et al. [2] employs patch-based sparse dictionary learing on events to address image reconstruction.”
BackgroundAsynchronous Spatial Image Convolutions for Event Cameras
Scheerlinck, C., Barnes, N. M., & Mahony, R. E. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2893427 · Cited by 65
Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisation
Reinbacher, C., Graber, G., & Pock, T. (2016) · British Machine Vision Conference (BMVC) · doi:10.5244/c.30.9 · Cited by 63
Event-Based Sensing and Signal Processing in the Visual, Auditory, and Olfactory Domain: A Review
Najaran, M. H. T., & Schmuker, M. (2021) · Frontiers in Neural Circuits · doi:10.3389/fncir.2021.610446 · Cited by 60
“…2015; Vasco et al., 2016; Mueggler et al., 2017a; Alzugaray and Chli, 2018b), line detection (Seifozzakerini et al., 2016, 2017), face detection (Barua et al., 2016), Sun detection (Farian et al., 2015) Localization Localization (Weikersdorfer and Conradt, 2012; Yuan and Ramalingam, 2016),…”
BackgroundMethodEvent-driven Re-Id: A New Benchmark and Method Towards Privacy-Preserving Person Re-Identification
Ahmad, S., Scarpellini, G., Morerio, P., & Bue, A. D. (2022) · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw54805.2022.00052 · Cited by 54
“…modality is a step towards privacy-preserving vision but recent advancements have shown that it is indeed possible to recover grayscale images from event streams using patch-based dictionaries [3], variational models [24], photometric constancy [28], and deep learning-based solutions [30, 37, 6].”
BackgroundAsynchronous event-based clustering and tracking for intrusion monitoring in UAS
Gómez, J. P. R., Eguíluz, A. G., Dios, J. R. M., & Ollero, A. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197341 · Cited by 50
“Existing event-based surveillance methods rely on static cameras [12] [13].”
BackgroundMethodHyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks
Ercan, B., Eker, O., Saglam, C., Erdem, A., & Erdem, E. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3372460 · Cited by 56
“[21] were the first to show that motion estimation is not necessary for intensity image reconstruction, employing a patch-based dictionary learning method.”
BackgroundLearning Event Guided High Dynamic Range Video Reconstruction
Yang, Y., Han, J. H., Liang, J., Sato, I., & Shi, B. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01338 · Cited by 46
“Other methods [3, 4] optimized a variational model to reconstruct intensity images.”
Inceptive Event Time-Surfaces for Object Classification Using Neuromorphic Cameras
Baldwin, R. W., Almatrafi, M., Kaufman, J. R., Asari, V. K., & Hirakawa, K. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-27272-2_35 · Cited by 44
“They report only changes in the pixel intensity, requiring a new set of techniques to perform basic image processing and computer vision tasks—examples include optical flow [3,8], feature extraction [4,12,13], gesture recognition [2,11], and object recognition [5,14].”
A Residual Learning Approach to Deblur and Generate High Frame Rate Video With an Event Camera
Chen, H., Teng, M., Shi, B., Wang, Y., & Huang, T. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3199556 · Cited by 40
“Event cameras have been used in various computer vision tasks, such as high dynamic range (HDR) imaging [21], [22], face detection [23], object classification [24], and optical flow estimation [25] by converting events to images [21], [25] or using events directly [22], [23], [24] in the inference…”
MethodPerson Re-Identification without Identification via Event Anonymization
Ahmad, S., Morerio, P., & Del Bue, A. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01022 · Cited by 39
“…the events-stream encodes the complete visual signal in an extremely compressed form and recent works were able to decompress it and recover a standard (grayscale) visual output, either using patch-based dictionaries [3], variational models [28], or deep learning-based solutions [32, 30, 37, 43].”
BackgroundEvent-Driven Video Frame Synthesis
Wang, Z. W., Jiang, W., He, K. F., Shi, B., Katsaggelos, A. K., & Cossairt, O. S. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00532 · Cited by 38
Duan, P., Wang, Z. W., Shi, B., Cossairt, O. S., Huang, T., & Katsaggelos, A. K. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3113344 · Cited by 42
“We follow a previous approach that employs Poisson reconstruction for HDR reconstruction [64].”
MethodZhang, Z., Yezzi, A. J., & Gallego, G. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3230727 · Cited by 42
High Speed and High Dynamic Range Video with an Event Camera
Rebecq, H., Ranftl, R., Koltun, V., & Scaramuzza, D. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2963386 · Cited by 50
“As a remedy, earlier works have proposed hand-crafted image priors to constrain the problem [2], [3], [4], [5].”
MethodPhotorealistic image reconstruction from hybrid intensity and event-based sensor
Shedligeri, P., & Mitra, K. (2019) · Journal of Electronic Imaging · doi:10.1117/1.jei.28.6.063012 · Cited by 31
“ensor or the event sensor. 2. Related work Intensity image reconstruction from events: The proposed work is very closely related to other previous works which reconstruct intensity images from events [1, 3, 16]. Barua et al. [3] learn a dictionary from simulated event frames and their corresponding gradient images. Ba…”
ResultEmerging Trends and Applications of Neuromorphic Dynamic Vision Sensors: A Survey
Aliakbarpour, H., Moori, A., Khoramdel, J., Blasch, E., & Tahri, O. (2024) · IEEE Sensors Reviews · doi:10.1109/sr.2024.3513952 · Cited by 40
E2SRI: Learning to Super-Resolve Intensity Images From Events
Mostafavi, M., Nam, Y., Choi, J., & Yoon, K. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3096985 · Cited by 30
“Despite recent advances in stacking methods [1], [2], [6], [35], [42], our network performs well with a simple stacking method, such as stacking based on the number of events (SBN) or stacking based on time (SBT) [36].”
MethodHybrid Deblur Net: Deep Non-Uniform Deblurring With Event Camera
Zhang, L., Zhang, H., Chen, J., & Wang, L. (2020) · IEEE Access · doi:10.1109/access.2020.3015759 · Cited by 28
Cohen-Duwek, H., Shalumov, A., & Tsur, E. E. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00147 · Cited by 27
“Barua and colleagues also proposed reconstructing images from events by optimizing a sparse patch-based dictionary to match event patches with gradient patches using a simulator [26].”
BackgroundDetecting Stable Keypoints from Events through Image Gradient Prediction
Chiberre, P., Perot, E., Sironi, A., & Lepetit, V. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00153 · Cited by 31
“The first efforts in video and gradients reconstruction were made by [36] using a K-SVD algorithm to learn patch-based dictionary atoms.”
MethodCladera, F., Bisulco, A., Kepple, D. R., Isler, V., & Lee, D. D. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9191148 · Cited by 30
“Reconstruction approaches use various forms of integration of the DVS events over time to form an approximate frame-based image at a given time [4, 5, 6].”
BackgroundEnd-to-End Learning of Representations for Asynchronous Event-Based Data
Gehrig, D., Loquercio, A., Derpanis, K. G., & Scaramuzza, D. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00573 · Cited by 421
“From this line of research, typical high-level applications are gesture recognition [31], object recognition [29,45,59] or face detection [6].”
BackgroundLens less Cameras for Face Detection and Verification
Anushka, R. L., Jagadish, S., Satyanarayana, V., & Singh, M. K. (2021) · International Conference on Signal Processing, Computing and Control (ISPCC) · doi:10.1109/ispcc53510.2021.9609392 · Cited by 24
High-speed video generation with an event camera
Liu, H., Zhang, F., Marshall, D., Shi, L., & Hu, S. (2017) · The Visual Computer · doi:10.1007/s00371-017-1372-y · Cited by 24
“Current event camera research focuses on reconstructing grayscale images from event streams [4,12,19], while [7] restore grayscale images and videos from event streams in high-speed and high-dynamic-range scenes.”
BackgroundLearning to Deblur and Generate High Frame Rate Video with an Event CameraPreprint
Haoyu, C., Teng, M., Shi, B., YIzhou, W., & Tiejun, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00847 · Cited by 23
“Event cameras have been applied to various computer vision tasks by making compatible representations with image-based computer vision algorithms [27, 2, 33, 39].”
MethodEvent-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurring
Zhang, H., Zhang, L., Dai, Y., Li, H., & Koniusz, P. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01708-3 · Cited by 30
“[2] proposed to learn a sparse patch-based dictionary to match event patches with gradient patches, then use the so-called Poison integration to reconstruct the intensity images.”
MethodLearning to Super-Resolve Blurry Images With Events
Yu, L., Wang, B., Zhang, X., Zhang, H., Yang, W. T., Liu, J., & Xia, G.-S. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3240397 · Cited by 25
“[69] propose a learning-based approach to smooth the image gradients by imposing sparsity regularization and then”
BackgroundShariff, W., Dilmaghani, M. S., Kielty, P., Lemley, J., Farooq, M. A., Khan, F., & Corcoran, P. (2023) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2023.3325656 · Cited by 27
“Moreover, there are a few more studies with event cameras which can be efficiently used for driver monitoring systems [33], [34].”
BackgroundJoint Data Collection and Resource Allocation for Distributed Machine Learning at the Edge
Chen, M., Wang, H., Meng, Z., Xu, H., Xu, Y., Liu, J., & Huang, H. (2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.3045436 · Cited by 20
“For example, the data upload rate (e.g., 300 Mbps [27]) does not exceed the edge server’s inbound bandwidth (e.g., 10 Gbps).”
BackgroundEvent Encryption for Neuromorphic Vision Sensors: Framework, Algorithm, and Evaluation
Du, B., Li, W., Wang, Z., Xu, M., Gao, T., Li, J., & Wen, H. (2021) · Sensors · doi:10.3390/s21134320 · Cited by 18
“A direct face detection approach has been designed in [15], which utilises random forest and chooses the histogram of oriented gradients as features.”
MethodFace Pose Alignment with Event Cameras
Savran, A., & Bartolozzi, C. (2020) · Sensors · doi:10.3390/s20247079 · Cited by 18
“[51] applied a patched-based model via dictionary learning.”
MethodAhmad, S., Morerio, P., & Del Bue, A. (2024) · IEEE Access · doi:10.1109/access.2024.3399539 · Cited by 16
“This decompression has been achieved using different methods, such as patch-based dictionaries [36], variational models [37], or deep learning-based techniques [8], [9], [10], [11].”
MethodEvent-Based Gesture and Facial Expression Recognition: A Comparative Analysis
Verschae, R., & Bugueno-Cordova, I. G. (2023) · IEEE Access · doi:10.1109/access.2023.3328220 · Cited by 19
“However, event-based facial expression recognition remains a largely unexplored territory, where research has mainly focused on face detection [7], [8], [9] and eye blinking/tracking [8], [10], [11].”
BackgroundMethodFaces in Event Streams (FES): An Annotated Face Dataset for Event Cameras
Bissarinova, U., Rakhimzhanova, T., Kenzhebalin, D., & Varol, H. A. (2024) · Sensors · doi:10.3390/s24051409 · Cited by 18
“Specifically, the model can detect a face at a distance of up to 150 cm from the camera.”
BackgroundMethodNeuromorphic face analysis: A survey
Becattini, F., Berlincioni, L., Cultrera, L., & Bimbo, A. D. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2024.11.009 · Cited by 16
Nie, K., Shi, X., Cheng, S., Gao, Z., & Xu, J. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3034148 · Cited by 16
Fine-Grained Video Deblurring with Event Camera
Zhang, L., Zhang, H., Zhu, C., Guo, S., Chen, J., & Wang, L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-67832-6_29 · Cited by 15
Sensing Diversity and Sparsity Models for Event Generation and Video Reconstruction from Events
Liu, S., & Dragotti, P. L. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3278940 · Cited by 19
“[35] introduced dictionary learning to solve this problem aiming to map event images to spatial gradients of the scene, and then intensity images can be”
BackgroundEnergy and Computation Efficient Audio-Visual Voice Activity Detection Driven by Event-Cameras
Savran, A., Tavarone, R., Higy, B., Badino, L., & Bartolozzi, C. (2018) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2018.00055 · Cited by 15
“Prior work with EC-based detection involves [5], [16].”
MethodDuan, P., Li, B., Yang, Y., Lou, H., Teng, M., Zhou, X., Ma, Y., & Shi, B. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3568333 · Cited by 19
Small Moving Object Detection and Tracking Based on Event Signals
Shu, Y., Sui, Y., Zhao, S., Zhi, C., & Liu, W. (2021) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc54389.2021.9674247 · Cited by 13
“[3] designs a patch-based model to reconstruct frames, and then apply face detection algorithm on the generated frames.”
BackgroundMethodNear-Chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection
Bisulco, A., Ojeda, F. C., Isler, V., & Lee, D. D. (2020) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi49217.2020.00050 · Cited by 14
Auto-Tuned Event-Based Perception Scheme for Intrusion Monitoring With UAS
Gómez, J. P. R., Eguíluz, A. G., Dios, J. R. M., & Ollero, A. (2021) · IEEE Access · doi:10.1109/access.2021.3066529 · Cited by 14
“Two methods for face detection using event cameras were presented in [9].”
BackgroundMethodEvent-based human intrusion detection in UAS using Deep Learning
Pérez-Cutiño, M.-A., Eguíluz, A. G., Dios, J. R. M., & Ollero, A. (2021) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas51884.2021.9476677 · Cited by 13
“The work in [3] compared the performance of traditional and event cameras for human faces detection, showing the viability of using only events for face detection.”
BackgroundMethodTemporal-Mapping Photography for Event Cameras
Bao, Y., Sun, L., Ma, Y., & Wang, K. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73001-6_4 · Cited by 15
Deep Polarization Reconstruction with PDAVIS Events
Mei, H., Wang, Z., Yang, X. S., Wei, X., & Delbrück, T. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02121 · Cited by 13
“[5] introduced the first learning approach to this task.”
BackgroundDetection of Binary Square Fiducial Markers Using an Event Camera
Sarmadi, H., Muñoz‐Salinas, R., Olivares-Méndez, M. A., & Medina-Carnicer, R. (2021) · IEEE Access · doi:10.1109/access.2021.3058423 · Cited by 13
“Researchers have already attempted to use these cameras for common computer vision problems which include object classification [40], image deblurring [41], face detection [42], person tracking [43], mosaicing [44], and 3D reconstruction [4], [45].”
BackgroundNeuroDFD: Towards Efficient Driver Face Detection with Neuromorphic Vision Sensor
Liu, P., Chen, G., Li, Z., Clarke, D., Liu, Z., Zhang, R., & Knoll, A. (2022) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm54641.2022.9959313 · Cited by 12
“[17] proposes the first event face detection method, which adopts HoG (histogram of oriented gradients) as descriptor and random forests as classifier.”
MethodMS-EVS: Multispectral event-based vision for deep learning based face detection
Himmi, S., Parret, V., Chhatkuli, A., & Gool, L. V. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00067 · Cited by 12
“Equivalently to image-based face detection, over the time, research shifted from the use of hand-crafted features (as in [4, 29]) to deep learning approaches.”
BackgroundEvents-To-Video: Bringing Modern Computer Vision to Event Cameras
Rebecq, H., Ranftl, R., Koltun, V., & Scaramuzza, D. (2019) · Zurich Open Repository and Archive (University of Zurich) · doi:10.48550/arxiv.1904.08298 · Cited by 11
“contrast to [4], we do not reconstruct individual intensity images from small windows of events, but instead reconstruct a temporally consistent video from a long stream of events (several seconds) using a recurrent network.”
BackgroundGouda, M., Lugnan, A., Dambre, J., den Branden, G. V., Posch, C., & Bienstman, P. (2023) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/jstqe.2023.3244040 · Cited by 12
“In other words, its working principle inherently filters out temporally-redundant information [9], [16], [17], [18].”
BackgroundSundar, V., Dutson, M., Ardelean, A., Bruschini, C. E., Edoardo Charbon, A., & Gupta, M. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02362 · Cited by 10
Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation
Huang, C. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534386 · Cited by 10
EGST: An Efficient Solution for Human Gaits Recognition Using Neuromorphic Vision Sensor
Chen, L., Zhang, Z., Xiao, Y., & Wang, Y. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3409167 · Cited by 9
“…perception tasks, such as optical flow estimation [4], [5], [6], [7], feature detection and tracking [8], [9], 3D reconstruction monocular and stereo [10], [11], [12], visual odometry/SLAM [13], [14], image reconstruction [15], [16], motion segmentation [17], and recognition [18], [19], [20], [21].”
BackgroundMethodInfluentialEvent Stream Denoising Method Based on Spatio-Temporal Density and Time Sequence Analysis
Jiang, H., Wang, X., Tang, W., Song, Q., Song, Q., & Hao, W. (2024) · Sensors · doi:10.3390/s24206527 · Cited by 10
“In addition, event cameras show potential applications in visual navigation and localization [21–23].”
Choi, J., Choi, E., Choi, S., & Lee, W. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.07.020 · Cited by 11
Optimization of Event Camera Bias Settings for a Neuromorphic Driver Monitoring System
Dilmaghani, M. S., Shariff, W., Farooq, M. A., Lemley, J., & Corcoran, P. (2024) · IEEE Access · doi:10.1109/access.2024.3371487 · Cited by 10
“Authors in [23] proposed direct face detection and video reconstruction from event cameras.”
BackgroundNighttime traffic object detection via adaptively integrating event and frame domains
Jiang, Y. L., Wang, Y., Zhao, M., Zhang, Y., & Qi, H. (2023) · Fundamental Research · doi:10.1016/j.fmre.2023.08.004 · Cited by 9
Face Detection Using Hybrid SNN-ANN to Process Neuromorphic Event Stream
Shariff, W., Kielty, P., Lemley, J., & Corcoran, P. (2025) · IEEE Access · doi:10.1109/access.2025.3527160 · Cited by 8
Ge, C., Fu, X., He, P., Wang, K., Cao, C., & Zha, Z.-J. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i3.32319 · Cited by 8
Unsupervised Event-Based Video Reconstruction
Fox, G., Pan, X., Tewari, A., Elgharib, M. A., & Theobalt, C. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00413 · Cited by 8
“Most current solutions use neural networks [7,10,17,19,20,25,28–32, 34 , 35,37,38 , 41] while some do not [ 1,2,13, 15, 16, 24”
Event Cameras Meet SPADs for High-Speed, Low-Bandwidth Imaging
Muglikar, M., Somasundaram, S., Dave, A., Edoardo Charbon, A., Raskar, R., & Scaramuzza, D. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3576698 · Cited by 7
“Significant advancement was done by learning to reconstruct images from events [14], [15].”
Towards UAS Surveillance using Event Cameras
Dios, J. R. M., Eguíluz, A. G., Gómez, J. P. R., Tapia, R., & Ollero, A. (2020) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr50563.2020.9292606 · Cited by 7
“Two methods for face detection using event cameras were presented in [8] and compared the performance of using traditional and event cameras at detecting human faces, showing the viability of using only events for face detection.”
MethodFully Convolutional Event-camera Voice Activity Detection Based on Event Intensity
Savran, A. (2023) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu58738.2023.10296754 · Cited by 7
“There are several EC-based facial processing studies apart from visual speech as well, as on eye-blink detection [32], [33], face pose alignment [34], and face detection [35].”
BackgroundFast Retinomorphic Event-Driven Representations for Video Gameplay and Action Recognition
Chen, H., Liu, W., Goel, R., Lua, R. C., Mittal, S., Huang, Y., Veeraraghavan, A., & Patel, A. (2019) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2019.2948755 · Cited by 8
“multi-view stereo [57], high-speed tracking [49], panoramic tracking [59], face detection and intensity reconstruction [7], visual odometry [16], [58], motion flow [6] and real-time 3D”
Self-citationQR-code Reconstruction from Event Data via Optimization in Code Subspace
Nagata, J., Sekikawa, Y., Hara, K., Suzuki, T., & Aoki, Y. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093493 · Cited by 7
“[2] proposed the method of patch-based image reconstruction from event data by using learned a dictionary for mapping integrated events to image gradients.”
MethodMulti-timescale boosting for efficient and improved event camera face pose alignment
Savran, A. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103817 · Cited by 6
Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation
Kostadinov, D., & Scaramuzza, D. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412631 · Cited by 7
“stream were used for high-level applications like gesture recognition [22], object recognition [27], [4] or face detection [7].”
UAV human teleoperation using event-based and frame-based cameras
Gómez, J. P. R., Tapia, R., Eguíluz, A. G., Dios, J. R. M., & Ollero, A. (2021) · Aerial Robotic Systems Physically Interacting with the Environment (AIRPHARO) · doi:10.1109/airpharo52252.2021.9571049 · Cited by 6
Key-Nets: Optical Transformation Convolutional Networks for Privacy Preserving Vision Sensors
Byrne, J., DeCann, B., & Bloom, S. (2020) · British Machine Vision Conference (BMVC) · doi:10.5244/c.34.27 · Cited by 5
Wu, Z., Xia, Y., & Hu, R. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130136 · Cited by 5
Real-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEsPreprint
Giannone, G., Anoosheh, A., Quaglino, A., D’Oro, P., Gallieri, M., & Masci, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.03156 · Cited by 6
“ges, then apply existing computer vision techniques on these reconstructions. This is used, for example, in optical flow estimation (Bardow et al., 2016), SLAM (Kim et al., 2016) and face recognition (Barua et al., 2016). Such a process requires various filtering, tracking, and/or inertial measurement integration to pro…”
Event-based solutions for human-centered applications: a comprehensive review
Adra, M., Melcarne, S., Mirabet-Herranz, N., & Dugelay, J. (2025) · Frontiers in Signal Processing · doi:10.3389/frsip.2025.1585242 · Cited by 2
Review of visual reconstruction methods of retina-like vision sensors
朱, 林., & 田, 永. (2023) · Scientia Sinica Informationis · doi:10.1360/ssi-2021-0397 · Cited by 3
“图 1 [43,45 (cid:24) 47] 后来文献 [42,43,52] 表明 , 即使不需要估计运动 , 图像重建 也是可能的 .”
Extreme Early Image Recognition Using Event-Based Vision
Abubakar, A., AlHarami, A., Yang, Y., & Bermak, A. (2023) · Sensors · doi:10.3390/s23136195 · Cited by 3
“Recognition can sometimes be applied to events that are transformed to frames during inference [13,14], or by converting a trained neural network to a spiking neural network (SNN) which can operate on the event-based data directly [15–17].”
MethodPrivacy Protection of Sensitive Bioinformation Based on Event Cameras
Shen, Y., Dong, P., Zhang, Y., Chen, S., & Zheng, N. (2024) · Strategic Study of CAE · doi:10.15302/j-sscae-2024.01.017 · Cited by 3
“…。 利用变分能量最小化框架同步恢复场景的强度 图像和稠密光流 [83] ，是新的研究探索。其中的损失 事件流 [84] ，可在不明确估计光流的情况下，将恢复 强度的重构问题转化为能量最小化问题，显著降低 处理过程的复杂性。 基于补丁的稀疏字典建模事件流，是对真实事 件传感器数据的良好近似 [85] 。基于字典的先验信息 冲的类视网膜视觉图像重建架构 [86] 由运动局部激励 层、尖峰细化层、视觉重建层组成，其中的视觉重 建层由 LIF 神经元驱动，神经元之间的突触连接满 足尖峰时序依赖性可塑性规则。两阶段神经网络 [87] 整合了优化拉普拉斯预测的 CNN 网络、优化泊松…”
Removing Blocking Artifacts in Video Streams Using Event CamerasPreprint
Chopp, H., Banerjee, S., Cossairt, O. S., & Katsaggelos, A. K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.05973 · Cited by 3
“Baura et al. [20] and Rebecq et al. [21] were early adopters of using learning methods to reconstruct intensity images from only events.”
Event-based video reconstruction via attention-based recurrent network
Ma, W., Ma, S., Meiresone, P., Allebosch, G., Philips, W. R., & Aelterman, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129776 · Cited by 2
EdinoGait: Transferring Large Visual Models to Event-Based Vision for Enhancing Gait Recognition
Chen, L., Zhang, Z., & Wang, Y. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3623551 · Cited by 2
“…as optical flow estimation [18], [19], [20], [21] feature detection and tracking [22], [23], 3D reconstruction (monocular and stereo) [24], [25], [26] visual odometry/SLAM [27], [28], image reconstruction [29], [30], [31], [32], [32], motion segmentation [33], and recognition [34], [35], [36], [16].”
EventGAN: An Unsupervised Low-Light Grayscale Image Enhancement Method Based on Event Camera
Wu, Z., Xia, Y., Hu, R., & Gao, R. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3622656 · Cited by 2
“Barua et al. [25] demonstrated the practicality and robustness of patch-based models in both event-based video reconstruction and direct event-driven face detection tasks.”
Translation and Scale Invariance for Event-Based Object tracking
Pedersen, J. E., Singhal, R., & Conradt, J. (2023) · Neuro Inspired Computational Elements Conference (NICE) · doi:10.1145/3584954.3584996 · Cited by 3
“Other applications that have been explored with EBV data are corner detection [2], line detection [36], face detection [5], car detection [6], and hand gesture recognition [21].”
Background
Metadata
- Authors
- Miyatani, Y., Barua, S., & Veeraraghavan, A.
- Affiliations
- Rice University (US)
- Venue
- 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)
- Publisher
- IEEE
- Published
- 2016-03
- Volume
- 2016
- Pages
- 1-9
- ISSN
- 2472-6737 (ISSN-L)
- OpenAlex
- W2403865344
- Cited by
- 133
- References
- 37
- Citations by year
- 2026: 6 · 2025: 16 · 2024: 19 · 2023: 18 · 2022: 8 · 2021: 20 · 2020: 21 · 2019: 18 · 2018: 3 · 2017: 2 · 2016: 2
- FWCI
- 2.89
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Winter Conference on Applications of Computer Vision (publishedVersion)
- IEEE Conference Proceedings
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Keywords
- event cameras, event-based vision, face detection, video reconstruction, high-speed imaging, low-power vision, event stream processing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
