{"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/61","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":61,"pages_in_order":104,"rows_per_page":100,"rows":[6001,6100],"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/60","next":"/task/decoder/papers/62","papers":[{"url":null,"slug":"joint-depth-prediction-and-semantic","title":"Joint Depth Prediction and Semantic Segmentation with Multi-View SAM","date":"2023-10-31","arxiv_id":"2311.00134","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-principled-hierarchical-deep-learning","title":"A Principled Hierarchical Deep Learning Approach to Joint Image Compression and Classification","date":"2023-10-30","arxiv_id":"2310.19675","repositories_listed":0,"syntology":null},{"url":null,"slug":"bidirectional-captioning-for-clinically","title":"Improving Medical Visual Representations via Radiology Report Generation","date":"2023-10-30","arxiv_id":"2310.19635","repositories_listed":0,"syntology":null},{"url":null,"slug":"mentor-human-perception-guided-pretraining","title":"MENTOR: Human Perception-Guided Pretraining for Increased Generalization","date":"2023-10-30","arxiv_id":"2310.19545","repositories_listed":0,"syntology":null},{"url":null,"slug":"solarformer-multi-scale-transformer-for-solar","title":"SolarFormer: Multi-scale Transformer for Solar PV Profiling","date":"2023-10-30","arxiv_id":"2310.20057","repositories_listed":0,"syntology":null},{"url":null,"slug":"s2f-ner-exploring-sequence-to-forest","title":"S2F-NER: Exploring Sequence-to-Forest Generation for Complex Entity Recognition","date":"2023-10-29","arxiv_id":"2310.18944","repositories_listed":0,"syntology":null},{"url":null,"slug":"astormer-an-ast-structure-aware-transformer","title":"ASTormer: An AST Structure-aware Transformer Decoder for Text-to-SQL","date":"2023-10-28","arxiv_id":"2310.18662","repositories_listed":0,"syntology":null},{"url":null,"slug":"style-description-based-text-to-speech-with","title":"Style Description based Text-to-Speech with Conditional Prosodic Layer Normalization based Diffusion GAN","date":"2023-10-27","arxiv_id":"2310.18169","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-wireless-ai-generated-content-aigc","title":"A Wireless AI-Generated Content (AIGC) Provisioning Framework Empowered by Semantic Communication","date":"2023-10-26","arxiv_id":"2310.17705","repositories_listed":0,"syntology":null},{"url":null,"slug":"extended-signaling-methods-for-reduced-video","title":"Extended Signaling Methods for Reduced Video Decoder Power Consumption Using Green Metadata","date":"2023-10-26","arxiv_id":"2310.17346","repositories_listed":0,"syntology":null},{"url":null,"slug":"mo-yolo-end-to-end-multiple-object-tracking","title":"DecoderTracker: Decoder-Only Method for Multiple-Object Tracking","date":"2023-10-26","arxiv_id":"2310.17170","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-neonatal-chest-sound-separation","title":"Real-time Neonatal Chest Sound Separation using Deep Learning","date":"2023-10-26","arxiv_id":"2310.17116","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-neural-materials-using-block","title":"Real-Time Neural Materials using Block-Compressed Features","date":"2023-10-26","arxiv_id":"2311.16121","repositories_listed":0,"syntology":null},{"url":null,"slug":"synergynet-bridging-the-gap-between-discrete","title":"SynergyNet: Bridging the Gap between Discrete and Continuous Representations for Precise Medical Image Segmentation","date":"2023-10-26","arxiv_id":"2310.17764","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-point-model-with-autoencoding-and","title":"General Point Model with Autoencoding and Autoregressive","date":"2023-10-25","arxiv_id":"2310.16861","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-distributional-learning-via-cramer-wold","title":"Joint Distributional Learning via Cramer-Wold Distance","date":"2023-10-25","arxiv_id":"2310.16374","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-speech-driven-expressive-3d","title":"Personalized Speech-driven Expressive 3D Facial Animation Synthesis with Style Control","date":"2023-10-25","arxiv_id":"2310.17011","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-detr-spatially-disentangling-1","title":"Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection","date":"2023-10-24","arxiv_id":"2310.15955","repositories_listed":0,"syntology":null},{"url":null,"slug":"ldpc-decoding-with-degree-specific-neural","title":"LDPC Decoding with Degree-Specific Neural Message Weights and RCQ Decoding","date":"2023-10-24","arxiv_id":"2310.15483","repositories_listed":0,"syntology":null},{"url":null,"slug":"posterior-estimation-for-dynamic-pet-imaging","title":"Posterior Estimation for Dynamic PET imaging using Conditional Variational Inference","date":"2023-10-24","arxiv_id":"2310.15850","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-pre-trained-transformer-for-1","title":"Generative Pre-trained Transformer for Vietnamese Community-based COVID-19 Question Answering","date":"2023-10-23","arxiv_id":"2310.14602","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-timestamp-information-for","title":"Leveraging Timestamp Information for Serialized Joint Streaming Recognition and Translation","date":"2023-10-23","arxiv_id":"2310.14806","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentiment-analysis-with-adaptive-multi-head","title":"Sentiment analysis with adaptive multi-head attention in Transformer","date":"2023-10-23","arxiv_id":"2310.14505","repositories_listed":0,"syntology":null},{"url":null,"slug":"strong-and-efficient-baselines-for-open","title":"Strong and Efficient Baselines for Open Domain Conversational Question Answering","date":"2023-10-23","arxiv_id":"2310.14708","repositories_listed":0,"syntology":null},{"url":null,"slug":"vq-nerf-vector-quantization-enhances-implicit","title":"VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations","date":"2023-10-23","arxiv_id":"2310.14487","repositories_listed":0,"syntology":null},{"url":null,"slug":"conversational-speech-recognition-by-learning-1","title":"Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representation","date":"2023-10-22","arxiv_id":"2310.14278","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-quality-3d-face-reconstruction-with","title":"High-Quality 3D Face Reconstruction with Affine Convolutional Networks","date":"2023-10-22","arxiv_id":"2310.14237","repositories_listed":0,"syntology":null},{"url":null,"slug":"maru-a-manga-retrieval-and-understanding","title":"MaRU: A Manga Retrieval and Understanding System Connecting Vision and Language","date":"2023-10-22","arxiv_id":"2311.02083","repositories_listed":0,"syntology":null},{"url":null,"slug":"mfcc-gan-codec-a-new-ai-based-audio-coding","title":"MFCC-GAN Codec: A New AI-based Audio Coding","date":"2023-10-22","arxiv_id":"2310.14300","repositories_listed":0,"syntology":null},{"url":null,"slug":"separating-multiscale-battery-dynamics-and","title":"Separating multiscale Battery dynamics and predicting multi-step ahead voltage simultaneously through a data-driven approach","date":"2023-10-22","arxiv_id":"2310.14289","repositories_listed":0,"syntology":null},{"url":null,"slug":"fabula-intelligence-report-generation-using","title":"FABULA: Intelligence Report Generation Using Retrieval-Augmented Narrative Construction","date":"2023-10-20","arxiv_id":"2310.13848","repositories_listed":0,"syntology":null},{"url":null,"slug":"inter-scale-dependency-modeling-for-skin","title":"Inter-Scale Dependency Modeling for Skin Lesion Segmentation with Transformer-based Networks","date":"2023-10-20","arxiv_id":"2310.13727","repositories_listed":0,"syntology":null},{"url":null,"slug":"2d-3d-interlaced-transformer-for-point-cloud-1","title":"2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision","date":"2023-10-19","arxiv_id":"2310.12817","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-search-indexer-for-end-to-end-document","title":"Auto Search Indexer for End-to-End Document Retrieval","date":"2023-10-19","arxiv_id":"2310.12455","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-generative-modeling-for-images-3d","title":"Conditional Generative Modeling for Images, 3D Animations, and Video","date":"2023-10-19","arxiv_id":"2310.13157","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-long-range-transformers-you-need-to","title":"Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer","date":"2023-10-19","arxiv_id":"2310.12442","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-chatgpt-a-financial-expert-evaluating","title":"Is ChatGPT a Financial Expert? Evaluating Language Models on Financial Natural Language Processing","date":"2023-10-19","arxiv_id":"2310.12664","repositories_listed":0,"syntology":null},{"url":null,"slug":"lomae-low-level-vision-masked-autoencoders","title":"LoMAE: Low-level Vision Masked Autoencoders for Low-dose CT Denoising","date":"2023-10-19","arxiv_id":"2310.12405","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-hidden-waves-of-image","title":"Exploring Invariance in Images through One-way Wave Equations","date":"2023-10-19","arxiv_id":"2310.12976","repositories_listed":0,"syntology":null},{"url":null,"slug":"brain-decoding-toward-real-time","title":"Brain decoding: toward real-time reconstruction of visual perception","date":"2023-10-18","arxiv_id":"2310.19812","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-spectral-variational","title":"Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering","date":"2023-10-18","arxiv_id":"2310.11940","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-automatic-evaluation-methods-based","title":"Exploring Automatic Evaluation Methods based on a Decoder-based LLM for Text Generation","date":"2023-10-17","arxiv_id":"2310.11026","repositories_listed":0,"syntology":null},{"url":null,"slug":"focdepthformer-transformer-with-lstm-for","title":"FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stack","date":"2023-10-17","arxiv_id":"2310.11178","repositories_listed":0,"syntology":null},{"url":null,"slug":"hgcvae-integrating-generative-and-contrastive","title":"Refining Latent Representations: A Generative SSL Approach for Heterogeneous Graph Learning","date":"2023-10-17","arxiv_id":"2310.11102","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-shallow-fusion-of-backward-language","title":"Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognition","date":"2023-10-17","arxiv_id":"2310.11010","repositories_listed":0,"syntology":null},{"url":null,"slug":"medical-image-segmentation-via-sparse-coding","title":"Medical Image Segmentation via Sparse Coding Decoder","date":"2023-10-17","arxiv_id":"2310.10957","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-encoder-decoder-architectures-for","title":"Assessing Encoder-Decoder Architectures for Robust Coronary Artery Segmentation","date":"2023-10-16","arxiv_id":"2310.10002","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-multichannel-speaker-attributed","title":"End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis","date":"2023-10-16","arxiv_id":"2310.10106","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-and-improvement-of-segment","title":"Evaluation and improvement of Segment Anything Model for interactive histopathology image segmentation","date":"2023-10-16","arxiv_id":"2310.10493","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-music-and-language-attention-models-for","title":"Joint Music and Language Attention Models for Zero-shot Music Tagging","date":"2023-10-16","arxiv_id":"2310.10159","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-object-query-initialization-for-3d","title":"Multimodal Object Query Initialization for 3D Object Detection","date":"2023-10-16","arxiv_id":"2310.10353","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-high-binding-watermark-for","title":"Unified High-binding Watermark for Unconditional Image Generation Models","date":"2023-10-14","arxiv_id":"2310.09479","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantics-alignment-via-split-learning-for","title":"Semantics Alignment via Split Learning for Resilient Multi-User Semantic Communication","date":"2023-10-13","arxiv_id":"2310.09394","repositories_listed":0,"syntology":null},{"url":null,"slug":"clextract-recovering-highly-corrupted-dvb-gse","title":"CLExtract: Recovering Highly Corrupted DVB/GSE Satellite Stream with Contrastive Learning","date":"2023-10-12","arxiv_id":"2310.08210","repositories_listed":0,"syntology":null},{"url":null,"slug":"groot-learning-to-follow-instructions-by","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","date":"2023-10-12","arxiv_id":"2310.08235","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-robustness-and-properties","title":"Investigating the Robustness and Properties of Detection Transformers (DETR) Toward Difficult Images","date":"2023-10-12","arxiv_id":"2310.08772","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-pre-trained-cnns-and","title":"A Comparative Study of Pre-trained CNNs and GRU-Based Attention for Image Caption Generation","date":"2023-10-11","arxiv_id":"2310.07252","repositories_listed":0,"syntology":null},{"url":null,"slug":"rate-compatible-ldpc-neural-decoding-network","title":"Rate Compatible LDPC Neural Decoding Network: A Multi-Task Learning Approach","date":"2023-10-10","arxiv_id":"2310.06256","repositories_listed":0,"syntology":null},{"url":null,"slug":"solution-for-smart-101-challenge-of-iccv","title":"Solution for SMART-101 Challenge of ICCV Multi-modal Algorithmic Reasoning Task 2023","date":"2023-10-10","arxiv_id":"2310.06440","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-level-set-encoder-for-neural-distance","title":"HYVE: Hybrid Vertex Encoder for Neural Distance Fields","date":"2023-10-10","arxiv_id":"2310.06644","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-predictive-coding-of-intra","title":"Efficient Predictive Coding of Intra Prediction Modes","date":"2023-10-09","arxiv_id":"2310.05623","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-decode-the-surface-code-with-a","title":"Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Network","date":"2023-10-09","arxiv_id":"2310.05900","repositories_listed":0,"syntology":null},{"url":null,"slug":"locality-aware-generalizable-implicit-neural","title":"Locality-Aware Generalizable Implicit Neural Representation","date":"2023-10-09","arxiv_id":"2310.05624","repositories_listed":0,"syntology":null},{"url":"/paper/m3fpolypsegnet-segmentation-network-with","slug":"m3fpolypsegnet-segmentation-network-with","title":"M3FPolypSegNet: Segmentation Network with Multi-frequency Feature Fusion for Polyp Localization in Colonoscopy Images","date":"2023-10-09","arxiv_id":"2310.05538","repositories_listed":0,"syntology":null},{"url":null,"slug":"retseg-retention-based-colorectal-polyps","title":"RetSeg: Retention-based Colorectal Polyps Segmentation Network","date":"2023-10-09","arxiv_id":"2310.05446","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-studies-for-efficient-parameter","title":"Scaling Studies for Efficient Parameter Search and Parallelism for Large Language Model Pre-training","date":"2023-10-09","arxiv_id":"2310.05350","repositories_listed":0,"syntology":null},{"url":"/paper/towards-fine-grained-polyp-segmentation-and","slug":"towards-fine-grained-polyp-segmentation-and","title":"Towards Fine-Grained Polyp Segmentation and Classification","date":"2023-10-09","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-large-language-models-with","title":"Benchmarking Large Language Models with Augmented Instructions for Fine-grained Information Extraction","date":"2023-10-08","arxiv_id":"2310.05092","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-diffusion-model-for-medical-image","title":"Latent Diffusion Model for Medical Image Standardization and Enhancement","date":"2023-10-08","arxiv_id":"2310.05237","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforced-ui-instruction-grounding-towards-a","title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API","date":"2023-10-07","arxiv_id":"2310.04716","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-humanoid-motion-representations-for","title":"Universal Humanoid Motion Representations for Physics-Based Control","date":"2023-10-06","arxiv_id":"2310.04582","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-variational-multivariate-information","title":"Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses","date":"2023-10-05","arxiv_id":"2310.03311","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-contrastive-spoken-language","title":"Continual Contrastive Spoken Language Understanding","date":"2023-10-04","arxiv_id":"2310.02699","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-energy-efficiency-in-massive-mimo-a","title":"Enabling Energy-Efficiency in Massive-MIMO: A Scalable Low-Complexity Decoder for Generalized Quadrature Spatial Modulation","date":"2023-10-04","arxiv_id":"2310.02545","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-oriented-representation-learning-for","title":"Human-oriented Representation Learning for Robotic Manipulation","date":"2023-10-04","arxiv_id":"2310.03023","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-design-of-protein-sequence-and","title":"Joint Design of Protein Sequence and Structure based on Motifs","date":"2023-10-04","arxiv_id":"2310.02546","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-and-adapter-tuning-for-self","title":"Prompting and Adapter Tuning for Self-supervised Encoder-Decoder Speech Model","date":"2023-10-04","arxiv_id":"2310.02971","repositories_listed":0,"syntology":null},{"url":null,"slug":"talking-models-distill-pre-trained-knowledge","title":"Talking Models: Distill Pre-trained Knowledge to Downstream Models via Interactive Communication","date":"2023-10-04","arxiv_id":"2310.03188","repositories_listed":0,"syntology":null},{"url":null,"slug":"vits-based-singing-voice-conversion","title":"VITS-Based Singing Voice Conversion Leveraging Whisper and multi-scale F0 Modeling","date":"2023-10-04","arxiv_id":"2310.02802","repositories_listed":0,"syntology":null},{"url":null,"slug":"de-novo-drug-design-with-joint-transformers","title":"De Novo Drug Design with Joint Transformers","date":"2023-10-03","arxiv_id":"2310.02066","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-prompt-fine-tuning-of-foundation-models","title":"Multi-Prompt Fine-Tuning of Foundation Models for Enhanced Medical Image Segmentation","date":"2023-10-03","arxiv_id":"2310.02381","repositories_listed":0,"syntology":null},{"url":null,"slug":"nugget-2d-dynamic-contextual-compression-for","title":"Dodo: Dynamic Contextual Compression for Decoder-only LMs","date":"2023-10-03","arxiv_id":"2310.02409","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-before-you-speak-training-language","title":"Think before you speak: Training Language Models With Pause Tokens","date":"2023-10-03","arxiv_id":"2310.02226","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-masked-autoencoders-from-a","title":"Understanding Masked Autoencoders From a Local Contrastive Perspective","date":"2023-10-03","arxiv_id":"2310.01994","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-training-of-a-u-net-based","title":"Data Efficient Training of a U-Net Based Architecture for Structured Documents Localization","date":"2023-10-02","arxiv_id":"2310.00937","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoder-decoder-based-long-short-term-memory","title":"Encoder-Decoder Based Long Short-Term Memory (LSTM) Model for Video Captioning","date":"2023-10-02","arxiv_id":"2401.02052","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobilenvc-real-time-1080p-neural-video","title":"MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device","date":"2023-10-02","arxiv_id":"2310.01258","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-model-to-rule-them-all-towards-end-to-end","title":"One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition","date":"2023-10-02","arxiv_id":"2310.01688","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixel-aligned-recurrent-queries-for-multi-1","title":"Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection","date":"2023-10-02","arxiv_id":"2310.01401","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-vision-foundation-models-for-plant","title":"Adapting Vision Foundation Models for Plant Phenotyping","date":"2023-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"finger-unet-a-u-net-based-multi-task","title":"Finger-UNet: A U-Net based Multi-Task Architecture for Deep Fingerprint Enhancement","date":"2023-10-01","arxiv_id":"2310.00629","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-data-hiding-in-neural-compressed-latent","title":"Image Data Hiding in Neural Compressed Latent Representations","date":"2023-10-01","arxiv_id":"2310.00568","repositories_listed":0,"syntology":null},{"url":null,"slug":"cnn-based-automatic-segmentation-of-lumen","title":"CNN-based automatic segmentation of Lumen & Media boundaries in IVUS images using closed polygonal chains","date":"2023-09-29","arxiv_id":"2309.17406","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-the-query-based-object-detector-be","title":"Can the Query-based Object Detector Be Designed with Fewer Stages?","date":"2023-09-28","arxiv_id":"2309.16306","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-effective-nerfs-and-sdfs","title":"Learning Effective NeRFs and SDFs Representations with 3D Generative Adversarial Networks for 3D Object Generation: Technical Report for ICCV 2023 OmniObject3D Challenge","date":"2023-09-28","arxiv_id":"2309.16110","repositories_listed":0,"syntology":null},{"url":null,"slug":"t1-t2-relaxation-temporal-modelling-from","title":"T1/T2 relaxation temporal modelling from accelerated acquisitions using a Latent Transformer","date":"2023-09-28","arxiv_id":"2309.16853","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-sleep-decoder-aligning-awake-and","title":"SI-SD: Sleep Interpreter through awake-guided cross-subject Semantic Decoding","date":"2023-09-28","arxiv_id":"2309.16457","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-multi-tasking-for-speech-to-text","title":"Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing","date":"2023-09-27","arxiv_id":"2309.15826","repositories_listed":0,"syntology":null},{"url":null,"slug":"dualvc-2-dynamic-masked-convolution-for","title":"DualVC 2: Dynamic Masked Convolution for Unified Streaming and Non-Streaming Voice Conversion","date":"2023-09-27","arxiv_id":"2309.15496","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-dense-flow-field-for-highly-accurate","title":"Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization","date":"2023-09-27","arxiv_id":"2309.15556","repositories_listed":0,"syntology":null}],"record_sha256":"707d4e69e11d93917414d0f74d8149e826ef31e75152c8dd0d051d524d2a635a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}