standOff, and the article is at its publisher via the link below. When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.| relation to other work | claim_relations | how this paper stands to another: agrees, contradicts, extends, qualifies |
| claim type | claim_type | the shape of the claim: existence, mechanism, method, critique, prediction, null |
| concept edge | concept_edges | an asserted relation between two concepts, with the sentence asserting it |
| concept | concepts | an idea the paper works with, quoted where the paper uses it |
| content tag | content_tags | a finding, definition, quantity, statistic or variable named in the paper |
| contribution | contribution | what the paper claims to add |
| control | controls | an experiment run to eliminate a rival explanation |
| limitation | limitations | what the paper says its evidence cannot support |
| mechanism | mechanisms | how the reported effect is said to come about |
| method | method | how the paper produced its evidence |
| object of study | object_of_study | what the paper is about — the thing it investigates |
| phenomenon | phenomenon | the effect or regularity under study |
| research question | research_question | the question the paper sets itself |
| sense | senses | a distinct use of a term, quoted where the paper fixes it |
| transfer | transfers | a method or concept carried in from another field |
Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; none of 1 relation here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.
| facet | tag | field | conf. | whose words |
|---|---|---|---|---|
| object_of_study | 3D object detection from LiDAR point clouds, and the speed and orientation-accuracy limits of voxel-based convolutional detectors Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | object_of_study | the paper's words | |
| research_question | how to keep the information a 3D voxel representation preserves while removing the inference cost and the orientation error that come with it Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | research_question | the paper's words | |
| contribution | sparse convolution with a GPU rule-generation algorithm, a sine-error angle loss with a separate direction classifier, and ground-truth sampling augmentation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | contribution | the paper's words | |
| claim_type | method Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_type | the paper's words | |
| phenomenon | an ill-posed regression target: two orientation values that describe the same box but generate maximal loss against each other Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | phenomenon | the paper's words | |
| method | system-or-tool-building Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: system-or-tool-building | method | the paper's words | |
| mechanisms | objects and their enclosed points are collected once into a database, then pasted into other point clouds during training, which multiplies the labelled objects per scene and simulates each object in new surroundings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | mechanisms[0] | 0.95 | the tagger's words |
| mechanisms | pasted objects are removed when they intersect existing ones, so the augmentation cannot produce a scene that could not physically exist Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: collision rejection after sampling | mechanisms[1] | 0.95 | the tagger's words |
| mechanisms | each ground truth and its points are transformed independently instead of the whole cloud being transformed together, so the augmentation varies objects relative to their scene Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | mechanisms[2] | 0.95 | the tagger's words |
| limitations | performance is lower for pedestrians and cyclists and for bird's-eye-view detection, which the paper states in its own conclusion Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[0] | 0.95 | the tagger's words |
| limitations | pedestrians and cyclists give fewer points per instance and higher instance density, so they are more easily confused with clutter Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[1] | 0.95 | the tagger's words |
| limitations | test-server access was limited, so the larger model was evaluated on the test set only and the validation assessment covers the smaller model alone Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[2] | 0.95 | the tagger's words |
| transfers | the focal loss, carried from single-stage 2D image detection into 3D point-cloud detection to handle the same foreground-background imbalance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | transfers[0] | 0.95 | the tagger's words |
| controls | the same detector with dense convolution instead of sparse, to attribute the speed gain Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a speed gain produced by the rest of the detector rather than by sparse convolution · outcome: held | controls[0] | 0.95 | the tagger's words |
| controls | the angle encoding used by AVOD and ComplexYOLO, run as the comparison for the new angle loss Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a new angle loss credited with an improvement that the encoding used by the baselines would also have produced · outcome: held | controls[1] | 0.95 | the tagger's words |
| controls | a physical-plausibility check on the augmented scenes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a detector trained on augmented scenes containing objects that could not physically coexist, which would teach it geometry no sensor will ever show it · outcome: held | controls[2] | 0.95 | the tagger's words |
| controls | a validation-set assessment of the larger model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: over-fitting of the larger model to the test set - the validation-set assessment that would show it exists only for the smaller model, because access to the test server was limited · outcome: absent-declared-unreported | controls[3] | 0.95 | the tagger's words |
| concepts | sparse convolution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: sparse convolution | concepts[0] | 0.95 | the paper's words |
| concepts | angle regression Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: angle regression | concepts[1] | 0.95 | the paper's words |
| concepts | corner encoding Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: corner encoding | concepts[2] | 0.95 | the paper's words |
| concepts | direction classifier Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: direction classifier | concepts[3] | 0.95 | the paper's words |
| concepts | ground truths Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: ground truths | concepts[4] | 0.95 | the paper's words |
| concepts | anchors Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: anchors | concepts[5] | 0.95 | the paper's words |
| concepts | VoxelNet Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: VoxelNet | concepts[6] | 0.95 | the paper's words |
| concepts | KITTI Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: KITTI | concepts[7] | 0.95 | the paper's words |
| senses | 'orientation error' was measuring the ANGLE and not the BOX - two angles describing one box produced maximal loss Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[0] | 0.95 | the tagger's words |
| senses | the new loss treats boxes with opposite directions as the SAME by design, and a separate classifier recovers the direction Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[1] | 0.95 | the tagger's words |
| senses | the direction target is defined by a sign test on yaw: positive above zero, negative otherwise Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[2] | 0.95 | the tagger's words |
| senses | 'state of the art' here is dataset-relative: 90% AP for 2D car detection against 15% for 3D image-based Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[3] | 0.95 | the tagger's words |
| senses | 'real-time' is stated as a run time, not a claim - 20 fps for the large model and 40 for the small Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[4] | 0.95 | the tagger's words |
| claim_relations | extends → VoxelNet, which combines raw-point and voxel feature extraction end to end Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. note: keeps the voxel approach and replaces the dense 3D convolution that made it too slow | claim_relations[0] | the tagger's words | |
| claim_relations | critiques → prior angle encodings - corner, direct and vector Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. note: each is rejected for a different failure, and the replacement is a loss that changes what is being measured rather than how well | claim_relations[1] | the tagger's words | |
| claim_relations | builds-on → the focal loss introduced for single-stage detection Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_relations[2] | the tagger's words | |
| concept_edges | anchors —contrasted-with→ ground truths Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. differs in: count - about 70,000 anchors against a few ground truths each yielding 4 to 6 positives · strength of the relation: 0.95
Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span contrasts the NUMBERS of anchors and ground truths; contrasted-with is loose. also in: anchors · ground truths | concept_edges[2] | the tagger's words | |
| content_tags | sparse convolution gives a large speed gain over dense convolution at slight cost in performance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[0] | 0.95 | the tagger's words |
| content_tags | the new angle loss outperforms the vector encoding used by two prior detectors Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[1] | 0.95 | the tagger's words |
| content_tags | the method reaches state-of-the-art results using LiDAR alone Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[2] | 0.95 | the tagger's words |
| content_tags | performance remains lower for pedestrians and cyclists than for cars Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[3] | 0.95 | the tagger's words |
| content_tags | angle regression Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: angle regression | content_tags.definitions[0] | 0.95 | the tagger's words |
| content_tags | direction classifier Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: direction classifier | content_tags.definitions[1] | 0.95 | the tagger's words |
| content_tags | 90% AP for 2D car detection against 15% for 3D image-based car detection — None Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.quantities[0] | 0.95 | the tagger's words |
| content_tags | a factor-of-4 training speedup and factor-of-3 inference speedup against dense convolution — None Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.quantities[1] | 0.95 | the tagger's words |
| content_tags | about 0.025 s per frame for the small model on a GTX 1080 Ti — None Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.quantities[2] | 0.95 | the tagger's words |
| content_tags | 20 fps for the larger model and 40 fps for the smaller — None Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.quantities[3] | 0.95 | the tagger's words |
| content_tags | about 70,000 anchors per point cloud against a few ground truths giving 4 to 6 positives each — None Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.quantities[4] | 0.95 | the tagger's words |
| content_tags | average precision (AP) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: average precision (AP) | content_tags.statistics[0] | 0.95 | the tagger's words |
| content_tags | orientation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: orientation | content_tags.variables[0] | 0.95 | the tagger's words |
| content_tags | anchors Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: anchors | content_tags.variables[1] | 0.95 | the tagger's words |
Tags that could not be placed in the text:
What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.