Searcharxiv⌕ Search

arXiv subjects

Yifan Shuai

Publications and source records attributed to Yifan Shuai.

4 recordsLinked to original sources

When Reconstruction Helps Event-Camera Person Triggers

Event cameras record asynchronous changes in brightness. To use a general visual model as a recording trigger, a system must represent these measurements in a form the model can interpret. We compare direct grayscale accumulation, two temporal encodings, and two intensity reconstructors on paired real event data. On 192 windows from four held-out DSEC recordings, thresholds calibrated only on development data yielded 40 of 52 person detections and 12 of 140 background positives with E2VID. The strongest direct temporal encoding at an admissible fixed cutoff yielded 14 detections and seven background positives. A retrospective comparison at a common 10% background-positive cap yielded 40 detections for E2VID and at most 19 for any direct encoding. FireNet+ had lower preparation cost and produced 21 detections with zero observed background positives at its frozen cutoff. On the same 192 windows, Qwen3-VL-4B yielded 33/52, 2/140 with E2VID and 9/52, 9/140 with the highest-recall direct rendering, the three-bin image (person detections, background positives). A 96-second exploratory replay illustrates the sensitivity of episode capture and recording starts to cutoff selection. The experiments identify a detection benefit from reconstruction under controlled input history and distinguish it from the cost and false starts of continuous triggering.

cs.CV↗

Readout and Operating-Point Sensitivity in Event-Stream Candidate Selection

Event-triggered recording needs a useful combination of target capture and false triggers, yet representation comparisons can change with readout and threshold calibration. We evaluate real event accumulations from 520 DailyDVS-200 clips and 47 participants using participant-disjoint training, validation, and testing. The original study varies frozen encoder scale, accumulation duration, and temporal view count; a post-review extension adds two supervised-pretrained convolutional encoders, a 61,586-parameter trained CNN with three seeds, ten repeated participant partitions, and calibration sensitivity. At 50 ms/eight views under the primary handshake-or-fall policy, DINO-S CLS captures 101/132 targets with 40/388 false triggers, versus 78/132 and 35/388 for patch mean. DINO-B CLS has lower selected-threshold capture but higher fold-wise low-FPR partial AUC (0.746 versus 0.732). MobileNetV3-Small captures 97/132 with 53/388 false triggers, demonstrating why lightweight baselines and actual operating points matter. Across ten dependent repartitions, mean normalized partial AUC is 0.738 for DINO-B CLS and 0.674 for MobileNet. The original LeJEPA S-to-B capture difference is 8.3 points, but its multiplicity-adjusted interval includes zero. Duration and view-count effects remain policy dependent. We find no established JEPA-specific advantage. The evidence concerns offline action-defined candidate selection on previously used development data; it does not establish personal recording value, continuous false alarms per hour, or eyewear energy.

cs.CV↗

Separating mixtures of single-fiber orientation distributions for increased sensitivity to crossing white matter fibers

Intro: Diffusion MRI allows for in vivo probing of brain tissue architecture via micron-level diffusion aggregated at the millimeter scale, but crossing white matter fibers decrease the sensitivity of downstream tasks such as microstructural modeling and tractography. Current fixel-based methods for identifying the number, orientation, and spread of fibers rely on finding the peaks of fiber orientation distributions from constrained spherical deconvolution. However, this method is biased by the spreads of nearby fibers and fails at angular separations lower than approximately 40-50 degrees. Methods: In this work, we perform a constrained nonlinear optimization called fiber segmentation by signal splitting and iterative least squares estimation (FISSILE), modeling each voxel as a mixture of single-fiber distributions. We use FISSILE to fit axially symmetric fibers in simulations and on three in vivo human subjects from the Human Connectome Project, an ex vivo raccoon brain, as well as the same human subject scanned twice at two different signal-to-noise ratios (SNRs). Results: On simulated data, FISSILE successfully identifies fibers at an angular separation of 40° and a volume fraction of 0.1 at an SNR as low as 30, while MRtrix3's fod2fixel is limited to 60° separation and 0.1 volume fraction at the same SNR. On acquired data, FISSILE identified 85.8% of white matter voxels on average in human brains and 79.4% in the raccoon with at least one fiber crossing, whereas fod2fixel identified 30.1% and 44.5%. The number of white matter fiber crossings was mildly sensitive to different noise levels in the human subject with two acquisitions. Conclusion: A method that models the crossing fiber phenomenon as an unmixing problem increases sensitivity to individual fibers for more precise characterization of anatomy.

eess.IV↗

A Hands-On Workshop for Constructing a Low-Field MRI System in Three Days

Access to Magnetic Resonance Imaging system assembly knowledge can be expanded by leveraging open-source hardware and software, simplified installation requirements, and collaborative training initiatives. To this end, we conducted a three-day workshop to construct an operational 0.27T MRI scanner. The workshop hosted 16 participants, including faculty, postdoctoral fellows, trainers, and students, who collaborated to build the scanner using open-source hardware and software components. Teams were designated to focus on various subsystems, including the magnet, passive shimming, radiofrequency (RF) coils, gradient coils, data acquisition, and reconstruction. Pre-workshop preparation involved simulation-based design processes and fabrication techniques, which incorporated configuring MaRCoS and PyPulseq libraries, CNC machining, and 3D printing. During the workshop, participants assembled an H-shaped magnet, which achieved a peak magnetic field strength of 0.269T. Passive shimming effectively reduced the field inhomogeneity from 3mT to 2mT. A 3 cm diameter RF solenoid was built and tuned to 11.4 MHz. The gradients exhibited less than 5% non-linearity in simulations and were fabricated by CNC machining copper plates. The assembled system was used to acquire a 2D spin echo of a water phantom. Following the workshop, the system was further optimized to scan relaxometry phantoms. A post-workshop survey was carried out, revealing over 87% satisfaction. The constructed scanner represents a valuable platform for educational initiatives, pulse sequence development, and preclinical research imaging efforts.

physics.ins-det↗