Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks100 from public data
- The Sixth Visual Object Tracking VOT2018 Challenge Results804
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative; results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years.
- A Twofold Siamese Network for Real-Time Object Tracking672
The proposed SA-Siam outperforms all other real-time trackers by a large margin on OTB-2013/50/100 benchmarks and proposes a channel attention mechanism for the semantic branch.
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs639
Despite its compact 3.8-billion-parameter size, this experimental version of Phi-4-Mini achieves reasoning performance on par with or surpassing significantly larger models, including DeepSeek-R1-Distill-Qwen-7B and DeepSeek-R1-Distill-Llama-8B.
- Compressive data gathering for large-scale wireless sensor networks628
This paper presents the first complete design to apply compressive sampling theory to sensor data gathering for large-scale wireless sensor networks and shows the efficiency and robustness of the proposed scheme.
- 496
- 473
- PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network412
This paper proposes a phase-and-harmonics-aware deep neural network (DNN), named PHASEN, which has the ability to handle detailed phase patterns and to utilize harmonic patterns, and outperforms previous methods by a large margin on four metrics.
- SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking263
The greatest challenge facing visual object tracking is the simultaneous requirements on robustness and discrimination power, and a SiamFC-based tracker, named SPM-Tracker, is proposed, to address the two requirements in two separate matching stages.
- Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning238
The 7B model develops advanced reasoning skills-such as reflection, verification, and summarization-that are absent from the logic corpus after training on just 5K logic problems, and demonstrates generalization abilities to the challenging math benchmarks AIME and AMC.
- 221
- Tracking by Instance Detection: A Meta-Learning Approach193
This work proposes a principled three-step approach to build a high-performance tracker based on two modern detectors RetinaNet and FCOS, and finds that model-agnostic meta-learning (MAML) offers a strategy to initialize the detector that satisfies the authors' needs.
- Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?128
An attention-free network called sMLPNet is built based on the existing MLP-based vision models, replacing the MLP module in the token-mixing step with a novel sparse MLP (sMLP) module that significantly reduces the number of model parameters and computational complexity.
- Make It Move: Controllable Image-to-Video Generation with Text Descriptions121
A Motion Anchor-based video GEnerator (MAGE) with an innovative motion anchor (MA) structure to store appearance-motion aligned representation is proposed to model the uncertainty and increase the diversity of TI2V task.
- StableAnimator: High-Quality Identity-Preserving Human Image Animation114
StableAnimator is presented, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.
- CCEdit: Creative and Controllable Video Editing via Diffusion Models97
This work presents CCEdit, a versatile generative video editing framework based on diffusion models that employs a novel trident network structure that separates structure and appearance control, ensuring precise and creative editing capabilities.
- ART•V: Auto-Regressive Text-to-Video Generation with Diffusion Models92
This work presents ART•V, an efficient framework for autoregressive video generation with diffusion models, and proposes masked diffusion model which implicitly learns which information can be drawn from reference images rather than network predictions, in order to reduce the risk of generating inconsistent appearances that cause drifting.
- Joint Time-Frequency and Time Domain Learning for Speech Enhancement86
A cross-domain framework named TFT-Net, which takes time-frequency spectrogram as input and produces time-domain waveform as output is presented, which achieves the highest SDR and SSNR among state-of-the-art methods on two major speech enhancement benchmarks.
- Seamless rate adaptation for wireless networking76
This paper designs a Seamless Rate Adaptation for wireless networking which achieves smooth rate adjustment in a broad dynamic range of channel conditions and proposes rate compatible modulation (RCM), in which modulation signals are incrementally generated from information bits through weighted mapping.
- Towards a Better Match in Siamese Network Based Visual Object Tracker59
This paper proposes two simple yet effective mechanisms, namely angle estimation and spatial masking, to address issues of Siamese network based trackers, and produces a tracker, named Siam-BM, which is the best-performing realtime tracker to date.
- 54
- StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation52
StableAvatar is presented, the first end-to-end video diffusion transformer that synthesizes infinite-length high-quality videos without post-processing and introduces a novel Time-step-aware Audio Adapter that prevents error accumulation via time-step-aware modulation.
- 48
- FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis46
FloVD leverages optical flow to represent the motions of the camera and moving objects and adopts a two-stage video synthesis pipeline consisting of optical flow generation and flow-conditioned video synthesis.
- 46
- 45
- 44
- Cactus: a hybrid digital-analog wireless video communication system43
By keeping spatial redundancy at the sender and properly utilizing it at the receiver, this paper discovers that it can build a more robust and even more efficient wireless video communication system than existing ones.
- Resource allocation for cloud-based free viewpoint video rendering for mobile phones42
Experimental results demonstrate that the proposed cloud-based FVV rendering solution can substantially improve video quality on mobile devices comparing with traditional approaches.
- 39
- 38
- MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation35
The appearance Noise Prior, a novel mechanism aimed at maintaining the capabilities of pre-trained 2D diffusion models, is introduced, a novel mechanism aimed at maintaining the capabilities of pre-trained 2D diffusion models in a Divide-and-Conquer strategy.
- MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion35
The proposed MotionFollower is a lightweight score-guided diffusion model for video motion editing that achieves an approximately 80% reduction in GPU memory while delivering superior motion editing performance and exclusively supporting large camera movements and actions.
- Spatiotemporal Fusion in 3D CNNs: A Probabilistic View33
This paper proposes to convert the spatiotemporal fusion strategies into a probability space, which allows us to perform network-level evaluations of various fusion strategies without having to train them separately, and generates new fusion strategies which achieve the state-of-the-art performance on four well-known action recognition datasets.
- ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL31
ReasonGen-R1 is introduced, a two-stage framework that first imbues an autoregressive image generator with explicit text-based "thinking" skills via supervised fine-tuning on a newly generated reasoning dataset of written rationales, and then refines its outputs using Group Relative Policy Optimization.
- LaMD: Latent Motion Diffusion for Image-Conditional Video Generation30
A latent motion diffusion (LaMD) framework, which consists of a motion-decomposed video autoencoder and a diffusion-based motion generator, which is able to efficiently generate realistic motion on a continuous latent space under multi-modal conditions, at a cost that is similar to that of image diffusion models.
- 30
- 30
- 29
- 29
- 29
- Unsupervised Visual Representation Learning by Tracking Patches in Video28
A Catch-the-Patch game for a 3D-CNN model to learn visual representations that would help with video-related tasks and is pleasantly surprised to find that CtP-pretrained representation achieves much higher action classification accuracy than its fully supervised counterpart on Something-Something dataset.
- 28
- 28
- 26
- 25
- 25
- 24
- Multi-Scale Group Transformer for Long Sequence Modeling in Speech Separation22
This paper proposes a novel variation of Transformer, named multi-scale group Transformer (MSGT), which significantly reduces the complexity, and multi- scale fusion, which retains Transform's ability to capture long-term dependency.
- Optimized DFT-spread OFDM based visible light communications with multiple lighting sources22
An optimization approach of lighting layout is proposed through making a trade-off between the strong interfered areas and the maximum delay spread inside, and a Gbit/s DFT-S-OFDM based multiple lighting VLC downlink prototype is achieved for the first time in the form of real-time baseband modem and compact size components.
- 22
- 21
- 19
- Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs17
This work delves into the task of pose-free novel view synthesis from stereo pairs, a challenging and pioneering task in 3D vision, with an innovative framework that seamlessly integrates 2D correspondence matching, camera pose estimation, and NeRF rendering, fostering a synergistic enhancement of these tasks.
- 17
- Swift17
This paper designs a novel hybrid digital-analog (HDA) solution to embrace the advantages of both solutions and avoid their drawbacks, and implements a system, named Swift, and performs extensive trace-driven evaluations based on a software-defined radio platform.
- Resource Allocation for Uncoded Multi-user Video Transmission over Wireless Networks16
An uncoded video transmission framework to deliver the multi-user video over wireless networks and three optimization strategies are proposed in this paper: minimizing the total distortion; minimizing the maximal distortion; and minimizing the summation of square root distortion.
- REDUCIO! Generating 1K Video Within 16 Seconds Using Extremely Compressed Motion Latents15
It is argued that videos contain significantly more redundant information than images, allowing them to be encoded with very few motion latents, allowing them to be encoded with very few motion latents in Reducio-VAE.
- 15
- 15
- 15
- 15
- 13
- 12
- Compressed sensing based video multicast12
This work investigates how properties of natural images can be exploited to improve the reconstruction performance by transmitting a small amount of side information and proposes a way of exploiting inter-frame correlation by extending only the decoder.
- 12
- LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation11
This work introduces an efficient fine-tuning framework that embeds an LLM into a pretrained CLIP while incurring almost the same training cost as regular CLIP fine-tuning.
- ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning11
This work introduces ViaRL, the first framework to leverage rule-based reinforcement learning (RL) for optimizing frame selection in intention-driven video understanding, and achieves a nearly 15\% improvement on Needle QA, which is required to search a specific needle within a long video and regarded as one of the most suitable benchmarks for evaluating temporal grounding.
- 11
- 10
- 10
- Joint decoding of stereo JPEG image Pairs9
This paper addresses the problem of joint decoding of stereo JPEG image pairs, and proposes to use the popular JPEG compression tools in the cameras, and focus on the joint decoding problem for quality enhancement.
- Posterior-Guided Neural Architecture Search8
A Bayesian approach to the NAS problem, the posterior-guided NAS (PGNAS) avoids tuning a number of hyper-parameters and enables a very effective architecture sampling in posterior probability space and naturally alleviates the mismatch between the sampled architecture and weights caused by the weight sharing.
- MageBench: Bridging Large Multimodal Models to Agents7
MageBench is introduced, a Multimodal reasoning benchmark built upon light-weight AGEnt environments that pose significant reasoning challenges and hold substantial practical value, and it is found that rule-based RL can significantly boost visual reasoning capabilities.
- 7
- Compressive cooperation for gaussian half-duplex relay channel6
Results show that compressive cooperation has great potential in both transmission efficiency and its adaptation capability to channel variations.
- 5
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- Filler Word Detection with Hard Category Mining and Inter-Category Focal Loss2
This paper proposes a novel filler word detection method that effectively addresses the challenge of easily confused fillers by adding auxiliary categories dynamically and applying an additional inter-category focal loss.
- 2
- Resan: A Residual Dual‐Attention Network for Abnormal Cardiac Activity Detection1
A residual dual‐attention network (ResAN) for the detection of abnormal cardiac activity using synchronized ECG and PCG signals, which achieves an accuracy of 96.1%, surpassing the performances of comparison models by 1.0% to 9.9% when using synchronized ECG and PCG signals.
- 1
- 1
- Driver's Gaze Zone Estimation in Realistic Driving Environment by Kinect1
A new driver’s gaze zone estimation framework designed for the naturalistic driving environment that combines head and eye information to estimate the gaze zone of the driver in both daytime and nighttime and has better performance compared to the reference in the daytime.
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.