--- title: 'SCB-Dataset: Classroom Behavior & NLP Benchmark' url: https://www.emergentmind.com/topics/scb-dataset type: topic --- # SCB-Dataset: Classroom Behavior & NLP Benchmark The term SCB-Dataset refers to several distinct, technically significant datasets across multiple domains, most notably education-focused behavior detection in classroom scenarios and natural language processing (notably English–Thai machine translation). The predominant usage in current literature, with broad impact on computer vision for education, is the Student Classroom Behavior Dataset. This family of datasets provides large-scale, real-world, multi-class annotations of classroom behaviors, establishing public benchmarks and enabling empirical advances in automated classroom analytics. ## 1. Taxonomy and Variants SCB-Dataset as a term primarily refers to a series of publicly released datasets targeting the fine-grained recognition of student (and sometimes teacher) behaviors via object detection or spatio-temporal models in classroom imagery. Distinct variants include: | Variant | Size / Annotations | Classes | Notable Paper / Release Year | |------------------------------------|-----------------------------|------------------|-----------------------------| | SCB-Dataset (YOLOv7 version) | 4,200 images, 18,400 boxes | Hand raising, reading, writing (3) | [2306.03318] (2023) | | SCB-Dataset (BRA + YOLOv7) | 4,001 images, 11,248 boxes | Standing, sitting, speaking, listening, walking, raising hands, reading, writing (8) | [2305.07825] (2023) | | SCB-Dataset3 | 5,686 images, 45,578 boxes | Hand-raising, reading, writing, using phone, bowing head, leaning table (6) | [2310.02522] (2023) | | SCB-ST-Dataset4 | 757,265 images, 25,810 boxes| Hand-raising, reading, writing (3) (spatio-temporal clips) | [2310.16267] (2023) | | SCBehavior / SCB-DETR Dataset | 1,346 images, 9,911 boxes | Writing, reading, looking up, turning head, raising hand, standing, discussing (7) | [2410.07834] (2024) | | SCB-Dataset (Student+Teacher) | 13,330 images, 122,977 boxes| 19 behaviors (student+teacher), 12 detection, 14 classification | [2304.02488] (2023) | | SCB Synthesis (for text editing) | 1,000,000 synthetic images | Style, content, background (text STE) | [2511.13399] (2025) | | SCB (Seeing Culture Benchmark) | 1,065 images, 3,178 MCQ | Visual reasoning, segmentation (cultural artifacts) | [2509.16517] (2025) | | SCB-MT-EN-TH-2020 | 1,000,000+ parallel segments| N/A (MT corpus: English–Thai) | [2007.03541] (2020) | The term "SCB-Dataset" is thus highly overloaded; in education-centric vision, it universally denotes *Student Classroom Behavior* datasets, while in other contexts (e.g., [2511.13399], [2509.16517], [2007.03541]) it is either part of a STE data synthesis construct, a cultural reasoning VQA benchmark, or denotes the "SCB" corpus for English–Thai MT. ## 2. Dataset Creation and Annotation Protocols The canonical SCB-Dataset ([2306.03318], [2305.07825], [2310.02522], [2310.16267], [2304.02488], [2410.07834]) is constructed from frame-level annotation of real-world classroom videos sourced from platforms such as bjyhjy, 1s1k, youke.qlteacher, and youke-smile.shec. Key aspects: - **Sampling Strategy:** Representative frames (3–15 per video) are drawn across a wide spectrum of camera angles (front/side/back), seating densities (occluded/dense), and learning stages (kindergarten to high school). - **Annotation Guidelines:** Bounding boxes are drawn tightly around each individual exhibiting a behavior of interest. For hand-raising, boxes include the hand and adjacent torso; reading/writing boxes encompass upper body and book/desk. Ambiguous or low-visibility instances (<20%) are excluded. Every annotation undergoes dual review to ensure label accuracy ([2306.03318]). - **Label Distribution:** SCB-Dataset3 ([2310.02522]) expands to six major behaviors, with detailed counts (e.g., reading: 18,667, hand-raising: 11,213). - **Format:** YOLO-style text files or COCO-JSON are prevalent; each image’s annotations are delivered as one file, specifying normalized class and box coordinates ([2306.03318], [2305.07825], [2310.02522], [2304.02488]). - **Advanced Datasets:** SCB-ST-Dataset4 ([2310.16267]) introduces automated spatio-temporal expansion from image datasets: per-frame labels from a seed image are propagated across video segments to construct short behavior clips, minimizing manual effort. ## 3. Dataset Splits, Balancing, and Class Distribution Splitting is typically 80% training, 20% validation ([2306.03318], [2305.07825], [2304.02488]). No explicit test set is given except in SCBehavior ([2410.07834]), which reports train/val/test (6,413/2,565/933 boxes). Class imbalance is persistent; for instance, in [2306.03318], reading is under-represented relative to writing and hand-raising. Balancing is achieved via class-weighted losses: $$ w_c = \frac{1}{n_c} $$ where $n_c$ is the class count. In more complex datasets ([2304.02488]), up/down-sampling is employed during frame extraction to increase rare class frequency. Final splits, especially for classification tasks, are explicit and stratified ([2304.02488], Table 3). ## 4. Evaluation Protocols and Metrics Detection evaluation is standardized on precision, recall, and mean Average Precision (mAP) at specified Intersection-over-Union (IoU) thresholds: $$ \text{Precision} = \frac{TP}{TP+FP} \quad \text{Recall} = \frac{TP}{TP+FN} $$ $$ \text{AP}_c(t) = \int_0^1 P_c(r) dr,\quad mAP@0.5 = \frac{1}{N_\text{classes}}\sum_{c=1}^{N_\text{classes}} AP_c(0.5) $$ mAP@0.5:0.95 (COCO-style) sweeps IoU from 0.50 to 0.95. For behavior similarity, [2310.02522] and [2310.16267] introduce the Behavior Similarity Index (BSI), quantifying the visual overlap between classes. For classification, macro-averaged F1, precision, and recall are reported ([2304.02488]). ## 5. Baseline Results and Model Comparisons SCB-Dataset benchmarks have driven empirical advances in detection accuracy across multiple network architectures: | Model Variant | mAP@0.5 (%) | Key Details | Source Paper | |-------------------------|-------------|------------------------------------------------|---------------------| | YOLOv7 (baseline) | 77.2 | Standard, SCB-Dataset (3 classes) | [2306.03318] | | YOLOv7 + BRA | 78.8 | Bi-level Routing Attention | [2306.03318] | | YOLOv7 + Wise-IoU v3 | 79.0 | +1.8% over baseline with improved IoU loss | [2306.03318] | | YOLOv7-BRA | 87.1 | 8-class, strong fusion with SlowFast | [2305.07825] | | YOLOv7x (SCB3-S) | 80.3 | Best in SCB3-S (3-class) | [2310.02522] | | YOLOv7x (SCB-ST) | 86.8 | Hand-raising class, spatio-temporal dataset | [2310.16267] | | SlowFast | 96.9 (HR) | Highest AP for hand-raising, weaker for writing| [2310.16267] | | YOLOv7 (teacher behaviors) | 94.0 | Largest scale, 12 detection classes | [2304.02488] | | SCB-DETR | 62.6 (mAP) | Multi-scale deformable transformer, 1.5% gain | [2410.07834] | A prominent trend is that models augmented with attention modules (BRA, Wise-IoU), multi-model fusion, or transformer-based architectures outperform vanilla object detectors, particularly in crowded and occluded scenes. ## 6. Data Access, Legal Framework, and Public Releases All variants of SCB-Dataset are openly available for academic use. Typical access mechanisms include: - **Primary repository:** https://github.com/Whiffe/SCB-dataset ([2306.03318], [2310.02522], [2310.16267], [2304.02488]) - **Licensing:** Open-source or educational research license (see repository LICENSE). - **Data format:** Images in JPEG/PNG, annotations in YOLO-style .txt or COCO-JSON; detailed schemas published for classification and detection ([2304.02488]). - **For NLP variant:** SCB-MT-EN-TH-2020 is CC-BY-SA 4.0, code at https://github.com/scb-mt/en-th-2020 ([2007.03541]). Some variants (e.g., SCB Synthesis for STE [2511.13399]) provide code for synthetic data generation and scripts for complex multi-attribute group construction. ## 7. Research Impact and Future Directions The SCB-Dataset series fills a critical void in large-scale, behavior-resolved datasets for classroom analytics, enabling: - Benchmarking novel detection architectures (YOLOv7, multi-scale transformer, multi-model fusion) in education. - Fair comparison on realistic, noisy, and occluded data spanning student age, pose, and class context. - Progress in advanced applications including engagement modeling, teacher effectiveness feedback, and context-aware content recommendation. Remaining challenges include class imbalance, under-representation of rare or confusable behaviors (notably “writing,” “bowing head,” “leaning table”), and the need for spatio-temporal action annotation beyond per-frame boxes. New directions cited in the literature are the expansion of annotated university scenes ([2310.02522]), joint temporal tracking, class-balanced training objectives, and integration with large vision–language models for holistic multi-modal AI in education. Other "SCB" datasets are domain-specific but methodologically relevant: scene text editing disentanglement ([2511.13399]), visual-cultural reasoning ([2509.16517]), and high-resource MT ([2007.03541]) further demonstrate the impact of careful multi-attribute annotation and robust open dataset construction. --- References: - "Student Classroom Behavior Detection based on Improved YOLOv7" [2306.03318] - "Student Classroom Behavior Detection based on YOLOv7-BRA and Multi-Model Fusion" [2305.07825] - "SCB-Dataset3: A Benchmark for Detecting Student Classroom Behavior" [2310.02522] - "Student Classroom Behavior Detection based on Spatio-Temporal Network and Multi-Model Fusion" [2310.16267] - "SCB-Dataset: A Dataset for Detecting Student and Teacher Classroom Behavior" [2304.02488] - "Multi-Scale Deformable Transformers for Student Learning Behavior Detection in Smart Classroom" [2410.07834] - "TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing" [2511.13399] - "Seeing Culture: A Benchmark for Visual Reasoning and Grounding" [2509.16517] - "scb-mt-en-th-2020: A Large English-Thai Parallel Corpus" [2007.03541] Source: https://www.emergentmind.com/topics/scb-dataset