{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/decoder/papers/62","list_of":"/task/decoder","task":"Decoder","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":62,"pages_in_order":104,"rows_per_page":100,"rows":[6101,6200],"of":10368,"counts":{"archive_papers_tagged":10368,"with_a_code_link":4358,"where_syntology_ran_a_sample":1061,"not_listed_spam_title":0,"listed":10368,"listed_where_code_ran":1061,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":909,"every_run_a_failure_of_syntologys_instrument":152,"listed_with_a_run_with_no_instrument_failure":909,"listed_every_run_a_failure_of_syntologys_instrument":152,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/decoder","prev":"/task/decoder/papers/61","next":"/task/decoder/papers/63","papers":[{"url":null,"slug":"msg-bart-multi-granularity-scene-graph","title":"MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation","date":"2023-09-26","arxiv_id":"2311.12820","repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-level-vectorized-beam-search-based-on","title":"Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference","date":"2023-09-26","arxiv_id":"2309.14922","repositories_listed":0,"syntology":null},{"url":null,"slug":"skip-connected-neural-networks-with-layout","title":"Skip-Connected Neural Networks with Layout Graphs for Floor Plan Auto-Generation","date":"2023-09-25","arxiv_id":"2309.13881","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-learning-sequential-decoder-for","title":"A Deep Learning Sequential Decoder for Transient High-Density Electromyography in Hand Gesture Recognition Using Subject-Embedded Transfer Learning","date":"2023-09-23","arxiv_id":"2310.03752","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithms-for-object-detection-in","title":"Algorithms for Object Detection in Substations","date":"2023-09-23","arxiv_id":"2311.07577","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-3-cs-multi-target-masked-point-modeling","title":"M$^3$CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders","date":"2023-09-23","arxiv_id":"2309.13235","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-context-aggregation-network-for","title":"Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects","date":"2023-09-22","arxiv_id":"2309.12641","repositories_listed":0,"syntology":null},{"url":"/paper/stemgan-spatio-temporal-generative","slug":"stemgan-spatio-temporal-generative","title":"STemGAN: spatio-temporal generative adversarial network for video anomaly detection","date":"2023-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"triple-view-knowledge-distillation-for-semi","title":"Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation","date":"2023-09-22","arxiv_id":"2309.12557","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-level-asymmetric-contrastive-learning","title":"Multi-level Asymmetric Contrastive Learning for Volumetric Medical Image Segmentation Pre-training","date":"2023-09-21","arxiv_id":"2309.11876","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-complex-u-net-with-conformer-for-audio","title":"Deep Complex U-Net with Conformer for Audio-Visual Speech Enhancement","date":"2023-09-20","arxiv_id":"2309.11059","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightning-fast-dual-layer-lossless-coding-for","title":"Lightning-Fast Dual-Layer Lossless Coding for Radiance Format High Dynamic Range Images","date":"2023-09-20","arxiv_id":"2309.11072","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-form-end-to-end-speech-translation-via","title":"Long-Form End-to-End Speech Translation via Latent Alignment Segmentation","date":"2023-09-20","arxiv_id":"2309.11384","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-image-compression-using-masked-sparse","title":"Neural Image Compression Using Masked Sparse Visual Representation","date":"2023-09-20","arxiv_id":"2309.11661","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-family-of-pretrained-transformer-language","title":"A Family of Pretrained Transformer Language Models for Russian","date":"2023-09-19","arxiv_id":"2309.10931","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-aware-feature-aggregation-network-for","title":"Edge-aware Feature Aggregation Network for Polyp Segmentation","date":"2023-09-19","arxiv_id":"2309.10523","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-speech-recognition","title":"End-to-End Speech Recognition Contextualization with Large Language Models","date":"2023-09-19","arxiv_id":"2309.10917","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-level-feature-fusion-network-combining","title":"Multi-level feature fusion network combining attention mechanisms for polyp segmentation","date":"2023-09-19","arxiv_id":"2309.10219","repositories_listed":0,"syntology":null},{"url":"/paper/roadformer-duplex-transformer-for-rgb-normal","slug":"roadformer-duplex-transformer-for-rgb-normal","title":"RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing","date":"2023-09-19","arxiv_id":"2309.10356","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-text-compression-for-classification","title":"Semantic Text Compression for Classification","date":"2023-09-19","arxiv_id":"2309.10809","repositories_listed":0,"syntology":null},{"url":null,"slug":"cb-whisper-contextual-biasing-whisper-using","title":"A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting","date":"2023-09-18","arxiv_id":"2309.09552","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-factorized-neural-transducer-model","title":"Improved Factorized Neural Transducer Model For text-only Domain Adaptation","date":"2023-09-18","arxiv_id":"2309.09524","repositories_listed":0,"syntology":null},{"url":null,"slug":"scribble-based-3d-multiple-abdominal-organ","title":"Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistency","date":"2023-09-18","arxiv_id":"2309.09730","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-quantification-of-autoencoder","title":"Uncertainty Quantification of Autoencoder-based Koopman Operator","date":"2023-09-18","arxiv_id":"2309.09419","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-frequency-assisted-transformer","title":"Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation","date":"2023-09-18","arxiv_id":"2309.09667","repositories_listed":0,"syntology":null},{"url":null,"slug":"clipunetr-assisting-human-robot-interface-for","title":"CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation","date":"2023-09-17","arxiv_id":"2309.09183","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoder-only-architecture-for-speech","title":"Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation","date":"2023-09-16","arxiv_id":"2309.08876","repositories_listed":0,"syntology":null},{"url":null,"slug":"chunked-attention-based-encoder-decoder-model","title":"Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition","date":"2023-09-15","arxiv_id":"2309.08436","repositories_listed":0,"syntology":null},{"url":null,"slug":"electroencephalogram-sensor-data-compression","title":"Electroencephalogram Sensor Data Compression Using An Asymmetrical Sparse Autoencoder With A Discrete Cosine Transform Layer","date":"2023-09-15","arxiv_id":"2309.12201","repositories_listed":0,"syntology":null},{"url":null,"slug":"occupancydetr-making-semantic-scene","title":"OccupancyDETR: Using DETR for Mixed Dense-sparse 3D Occupancy Prediction","date":"2023-09-15","arxiv_id":"2309.08504","repositories_listed":0,"syntology":null},{"url":null,"slug":"unist-towards-unifying-saliency-transformer","title":"UniST: Towards Unifying Saliency Transformer for Video Saliency Prediction and Detection","date":"2023-09-15","arxiv_id":"2309.08220","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-salient-object-detection-with-semantic","title":"Co-Salient Object Detection with Semantic-Level Consensus Extraction and Dispersion","date":"2023-09-14","arxiv_id":"2309.07753","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-text-to-speech-translation-system","title":"Direct Text to Speech Translation System using Acoustic Units","date":"2023-09-14","arxiv_id":"2309.07478","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-attention-based-encoder-decoder-model","title":"Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptation","date":"2023-09-14","arxiv_id":"2309.07369","repositories_listed":0,"syntology":null},{"url":null,"slug":"voxtlm-unified-decoder-only-models-for","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","date":"2023-09-14","arxiv_id":"2309.07937","repositories_listed":0,"syntology":null},{"url":null,"slug":"answering-subjective-induction-questions-on","title":"Answering Subjective Induction Questions on Products by Summarizing Multi-sources Multi-viewpoints Knowledge","date":"2023-09-12","arxiv_id":"2309.05938","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-post-processing-of-diffusion-tensor","title":"Efficient Post-processing of Diffusion Tensor Cardiac Magnetic Imaging Using Texture-conserving Deformable Registration","date":"2023-09-12","arxiv_id":"2309.06598","repositories_listed":0,"syntology":null},{"url":null,"slug":"mfpnet-multi-scale-feature-propagation","title":"MFPNet: Multi-scale Feature Propagation Network For Lightweight Semantic Segmentation","date":"2023-09-10","arxiv_id":"2309.04914","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-bit-aided-modulo-sampling-for-doa","title":"One-Bit-Aided Modulo Sampling for DOA Estimation","date":"2023-09-10","arxiv_id":"2309.04901","repositories_listed":0,"syntology":null},{"url":null,"slug":"denoising-mot-towards-multiple-object","title":"DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions","date":"2023-09-09","arxiv_id":"2309.04682","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-influencers-in-complex-networks-an","title":"Finding Influencers in Complex Networks: An Effective Deep Reinforcement Learning Approach","date":"2023-09-09","arxiv_id":"2309.07153","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-learning-of-force-based-motions-from","title":"Few-Shot Learning of Force-Based Motions From Demonstration Through Pre-training of Haptic Representation","date":"2023-09-08","arxiv_id":"2309.04640","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-enhancer-segmentation-network-fes-net","title":"Feature Enhancer Segmentation Network (FES-Net) for Vessel Segmentation","date":"2023-09-07","arxiv_id":"2309.03535","repositories_listed":0,"syntology":null},{"url":null,"slug":"ms-unet-v2-adaptive-denoising-method-and","title":"MS-UNet-v2: Adaptive Denoising Method and Training Strategy for Medical Image Segmentation with Small Training Data","date":"2023-09-07","arxiv_id":"2309.03686","repositories_listed":0,"syntology":null},{"url":null,"slug":"pbp-path-based-trajectory-prediction-for","title":"PBP: Path-based Trajectory Prediction for Autonomous Driving","date":"2023-09-07","arxiv_id":"2309.03750","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-neural-polar-codes-for-unknown","title":"Data-Driven Neural Polar Codes for Unknown Channels With and Without Memory","date":"2023-09-06","arxiv_id":"2309.03148","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-encoding-and-decoding-of-information","title":"Dynamic Encoding and Decoding of Information for Split Learning in Mobile-Edge Computing: Leveraging Information Bottleneck Theory","date":"2023-09-06","arxiv_id":"2309.02787","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-training-for-visual-tracking-with","title":"Efficient Training for Visual Tracking with Deformable Transformer","date":"2023-09-06","arxiv_id":"2309.02676","repositories_listed":0,"syntology":null},{"url":null,"slug":"epi-curriculum-episodic-curriculum-learning","title":"Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation","date":"2023-09-06","arxiv_id":"2309.02640","repositories_listed":0,"syntology":null},{"url":null,"slug":"gender-specific-machine-translation-with","title":"Gender-specific Machine Translation with Large Language Models","date":"2023-09-06","arxiv_id":"2309.03175","repositories_listed":0,"syntology":null},{"url":null,"slug":"stylebook-content-dependent-speaking-style","title":"Stylebook: Content-Dependent Speaking Style Modeling for Any-to-Any Voice Conversion using Only Speech Data","date":"2023-09-06","arxiv_id":"2309.02730","repositories_listed":0,"syntology":null},{"url":null,"slug":"bring-the-noise-introducing-noise-robustness","title":"Bring the Noise: Introducing Noise Robustness to Pretrained Automatic Speech Recognition","date":"2023-09-05","arxiv_id":"2309.02145","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-object-grounding-in-3d-scenes","title":"Dense Object Grounding in 3D Scenes","date":"2023-09-05","arxiv_id":"2309.02224","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-based-3d-object-detection-with","title":"Diffusion-based 3D Object Detection with Random Boxes","date":"2023-09-05","arxiv_id":"2309.02049","repositories_listed":0,"syntology":null},{"url":null,"slug":"radio-reference-agnostic-dubbing-video","title":"RADIO: Reference-Agnostic Dubbing Video Synthesis","date":"2023-09-05","arxiv_id":"2309.01950","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-wide-feedforward-is-all-you-need","title":"One Wide Feedforward is All You Need","date":"2023-09-04","arxiv_id":"2309.01826","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-where-it-matters-rethinking-visual","title":"Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration","date":"2023-09-03","arxiv_id":"2309.01131","repositories_listed":0,"syntology":null},{"url":null,"slug":"magma-music-aligned-generative-motion","title":"MAGMA: Music Aligned Generative Motion Autodecoder","date":"2023-09-03","arxiv_id":"2309.01202","repositories_listed":0,"syntology":null},{"url":null,"slug":"short-term-power-load-forecasting-method","title":"Short-term power load forecasting method based on CNN-SAEDN-Res","date":"2023-09-02","arxiv_id":"2309.07140","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-encoder-decoder-framework-for","title":"An Improved Encoder-Decoder Framework for Food Energy Estimation","date":"2023-09-01","arxiv_id":"2309.00468","repositories_listed":0,"syntology":null},{"url":null,"slug":"arfa-an-asymmetric-receptive-field","title":"ARFA: An Asymmetric Receptive Field Autoencoder Model for Spatiotemporal Prediction","date":"2023-09-01","arxiv_id":"2309.00314","repositories_listed":0,"syntology":null},{"url":null,"slug":"videogen-a-reference-guided-latent-diffusion","title":"VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation","date":"2023-09-01","arxiv_id":"2309.00398","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-policy-adaptation-method-for-implicit","title":"Foundational Policy Acquisition via Multitask Learning for Motor Skill Generation","date":"2023-08-31","arxiv_id":"2308.16471","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-mandarin-prosodic-structure","title":"Improving Mandarin Prosodic Structure Prediction with Multi-level Contextual Information","date":"2023-08-31","arxiv_id":"2308.16577","repositories_listed":0,"syntology":null},{"url":null,"slug":"ramp-retrieval-augmented-mos-prediction-via","title":"RAMP: Retrieval-Augmented MOS Prediction via Confidence-based Dynamic Weighting","date":"2023-08-31","arxiv_id":"2308.16488","repositories_listed":0,"syntology":null},{"url":null,"slug":"catalog-phrase-grounding-cpg-grounding-of","title":"Catalog Phrase Grounding (CPG): Grounding of Product Textual Attributes in Product Images for e-commerce Vision-Language Applications","date":"2023-08-30","arxiv_id":"2308.16354","repositories_listed":0,"syntology":null},{"url":null,"slug":"jais-and-jais-chat-arabic-centric-foundation","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","date":"2023-08-30","arxiv_id":"2308.16149","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-factual-accuracy-in-text","title":"Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selection","date":"2023-08-30","arxiv_id":"2308.15711","repositories_listed":0,"syntology":null},{"url":null,"slug":"triangular-code-near-optimal-linear-time","title":"Triangular code: Near-optimal linear time fountain code","date":"2023-08-30","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"killing-two-birds-with-one-stone-can-an-audio","title":"Killing two birds with one stone: Can an audio captioning system also be used for audio-text retrieval?","date":"2023-08-29","arxiv_id":"2308.15090","repositories_listed":0,"syntology":null},{"url":null,"slug":"lambo-large-language-model-empowered-edge","title":"LAMBO: Large AI Model Empowered Edge Intelligence","date":"2023-08-29","arxiv_id":"2308.15078","repositories_listed":0,"syntology":null},{"url":null,"slug":"saan-similarity-aware-attention-flow-network","title":"SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images","date":"2023-08-28","arxiv_id":"2308.14570","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-and-audio-are-images-a-cross-modal","title":"Video and Audio are Images: A Cross-Modal Mixer for Original Data on Video-Audio Retrieval","date":"2023-08-26","arxiv_id":"2308.13820","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-human-machine-joint-learning-framework-to","title":"A Human-Machine Joint Learning Framework to Boost Endogenous BCI Training","date":"2023-08-25","arxiv_id":"2309.03209","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-structure-for-improved-adaptability","title":"Decoupled Structure for Improved Adaptability of End-to-End Models","date":"2023-08-25","arxiv_id":"2308.13345","repositories_listed":0,"syntology":null},{"url":null,"slug":"business-metric-aware-forecasting-for","title":"Business Metric-Aware Forecasting for Inventory Management","date":"2023-08-24","arxiv_id":"2308.13118","repositories_listed":0,"syntology":null},{"url":null,"slug":"learned-local-attention-maps-for-synthesising","title":"Learned Local Attention Maps for Synthesising Vessel Segmentations","date":"2023-08-24","arxiv_id":"2308.12861","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-controllable-multi-task","title":"Efficient Controllable Multi-Task Architectures","date":"2023-08-22","arxiv_id":"2308.11744","repositories_listed":0,"syntology":null},{"url":null,"slug":"furnishing-sound-event-detection-with","title":"Leveraging Language Model Capabilities for Sound Event Detection","date":"2023-08-22","arxiv_id":"2308.11530","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-owl-vit-temporally-consistent-open","title":"Video OWL-ViT: Temporally-consistent open-world localization in video","date":"2023-08-22","arxiv_id":"2308.11093","repositories_listed":0,"syntology":null},{"url":null,"slug":"rt-monodepth-real-time-monocular-depth","title":"Real-time Monocular Depth Estimation on Embedded Systems","date":"2023-08-21","arxiv_id":"2308.10569","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-feedback-detr-for-temporal-action","title":"Self-Feedback DETR for Temporal Action Detection","date":"2023-08-21","arxiv_id":"2308.10570","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectral-graphormer-spectral-graph-based","title":"Spectral Graphormer: Spectral Graph-based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images","date":"2023-08-21","arxiv_id":"2308.11015","repositories_listed":0,"syntology":null},{"url":null,"slug":"tokensplit-using-discrete-speech","title":"TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition","date":"2023-08-21","arxiv_id":"2308.10415","repositories_listed":0,"syntology":null},{"url":null,"slug":"eddense-net-fully-dense-encoder-decoder","title":"EDDense-Net: Fully Dense Encoder Decoder Network for Joint Segmentation of Optic Cup and Disc","date":"2023-08-20","arxiv_id":"2308.10192","repositories_listed":0,"syntology":null},{"url":null,"slug":"hodn-disentangling-human-object-feature-for","title":"HODN: Disentangling Human-Object Feature for HOI Detection","date":"2023-08-20","arxiv_id":"2308.10158","repositories_listed":0,"syntology":null},{"url":null,"slug":"wmformer-nested-transformer-for-visible","title":"WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning","date":"2023-08-20","arxiv_id":"2308.10195","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributionally-robust-cross-subject-eeg","title":"Distributionally Robust Cross Subject EEG Decoding","date":"2023-08-19","arxiv_id":"2308.11651","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniap-towards-universal-animal-perception-in","title":"UniAP: Towards Universal Animal Perception in Vision via Few-shot Learning","date":"2023-08-19","arxiv_id":"2308.09953","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-tailored-handwritten-text-recognition","title":"A tailored Handwritten-Text-Recognition System for Medieval Latin","date":"2023-08-18","arxiv_id":"2308.09368","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-knowledge-tracing-is-an-implicit-dynamic","title":"Deep Knowledge Tracing is an implicit dynamic multidimensional item response theory model","date":"2023-08-18","arxiv_id":"2309.12334","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-language-models-with-custom-vocabularies","title":"OCR Language Models with Custom Vocabularies","date":"2023-08-18","arxiv_id":"2308.09671","repositories_listed":0,"syntology":null},{"url":null,"slug":"agglomerative-transformer-for-human-object","title":"Agglomerative Transformer for Human-Object Interaction Detection","date":"2023-08-16","arxiv_id":"2308.08370","repositories_listed":0,"syntology":null},{"url":null,"slug":"medoe-a-multi-expert-decoder-and-output","title":"MEDOE: A Multi-Expert Decoder and Output Ensemble Framework for Long-tailed Semantic Segmentation","date":"2023-08-16","arxiv_id":"2308.08213","repositories_listed":0,"syntology":null},{"url":null,"slug":"onuvs-online-feature-decoupling-framework-for","title":"OnUVS: Online Feature Decoupling Framework for High-Fidelity Ultrasound Video Synthesis","date":"2023-08-16","arxiv_id":"2308.08269","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-encoder-decoder-network-for","title":"A Graph Encoder-Decoder Network for Unsupervised Anomaly Detection","date":"2023-08-15","arxiv_id":"2308.07774","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-ctc-aed-model-with-integrated-ctc","title":"Improving CTC-AED model with integrated-CTC and auxiliary loss regularization","date":"2023-08-15","arxiv_id":"2308.08449","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-method-for-hybrid","title":"Method for Generating Synthetic Data Combining Chest Radiography Images with Tabular Clinical Information Using Dual Generative Models","date":"2023-08-15","arxiv_id":"2308.07573","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffsed-sound-event-detection-with-denoising","title":"DiffSED: Sound Event Detection with Denoising Diffusion","date":"2023-08-14","arxiv_id":"2308.07293","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-deep-learning-meets-multi-task-learning","title":"When Deep Learning Meets Multi-Task Learning in SAR ATR: Simultaneous Target Recognition and Segmentation","date":"2023-08-14","arxiv_id":"2308.07093","repositories_listed":0,"syntology":null}],"record_sha256":"6750859fd5d304784a1504c4e7ab8be693aabdc7b08f2ba88c28012102e20f35","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}