arXiv subjects

Dian Li

Publications and source records attributed to Dian Li.

35 records · Page 2Linked to original sources

arXiv2023

An evaluation strategy of the thermal conductance of semiconductor interfaces using ultraviolet light

In the previous studies, the ultraviolet light thermoreflectance (UV-TDTR) signal from bulk semiconducting samples cannot be well explained by a thermal models based on the assumption that the heat is both absorbed and probed near the surface. A thermoreflectance (TDTR) technique was developed to directly excite semiconductors using UV-TDTR. At λ = 400nm, the photon energy is much greater than most semiconducting bandgaps, potentially allowing semiconducting transducers to absorb light within about 10 nm of the surface, potentially enabling direct measurements of semiconductor-semiconductor interfaces. The thermoreflectance coefficient for some direct-bandgap semiconducting materials was measured. Thermal transport models were fitted to thermorefectance data collected from the system. The differences in the signal for semiconductors with different doping and nanostructure features were also studied, which should change the recombination rate. No significant changes to the signal were observed.

physics.app-ph↗

arXiv2023

HumTrans: A Novel Open-Source Dataset for Humming Melody Transcription and Beyond

This paper introduces the HumTrans dataset, which is publicly available and primarily designed for humming melody transcription. The dataset can also serve as a foundation for downstream tasks such as humming melody based music generation. It consists of 500 musical compositions of different genres and languages, with each composition divided into multiple segments. In total, the dataset comprises 1000 music segments. To collect this humming dataset, we employed 10 college students, all of whom are either music majors or proficient in playing at least one musical instrument. Each of them hummed every segment twice using the web recording interface provided by our designed website. The humming recordings were sampled at a frequency of 44,100 Hz. During the humming session, the main interface provides a musical score for students to reference, with the melody audio playing simultaneously to aid in capturing both melody and rhythm. The dataset encompasses approximately 56.22 hours of audio, making it the largest known humming dataset to date. The dataset will be released on Hugging Face, and we will provide a GitHub repository containing baseline results and evaluation codes.

cs.SD↗

arXiv2023

Unified Pretraining Target Based Video-music Retrieval With Music Rhythm And Video Optical Flow Information

Background music (BGM) can enhance the video's emotion. However, selecting an appropriate BGM often requires domain knowledge. This has led to the development of video-music retrieval techniques. Most existing approaches utilize pretrained video/music feature extractors trained with different target sets to obtain average video/music-level embeddings. The drawbacks are two-fold. One is that different target sets for video/music pretraining may cause the generated embeddings difficult to match. The second is that the underlying temporal correlation between video and music is ignored. In this paper, our proposed approach leverages a unified target set to perform video/music pretraining and produces clip-level embeddings to preserve temporal information. The downstream cross-modal matching is based on the clip-level features with embedded music rhythm and optical flow information. Experiments demonstrate that our proposed method can achieve superior performance over the state-of-the-art methods by a significant margin.

cs.MM↗

arXiv2023

TagGPT: Large Language Models are Zero-shot Multimodal Taggers

Tags are pivotal in facilitating the effective distribution of multimedia content in various applications in the contemporary Internet era, such as search engines and recommendation systems. Recently, large language models (LLMs) have demonstrated impressive capabilities across a wide range of tasks. In this work, we propose TagGPT, a fully automated system capable of tag extraction and multimodal tagging in a completely zero-shot fashion. Our core insight is that, through elaborate prompt engineering, LLMs are able to extract and reason about proper tags given textual clues of multimodal data, e.g., OCR, ASR, title, etc. Specifically, to automatically build a high-quality tag set that reflects user intent and interests for a specific application, TagGPT predicts large-scale candidate tags from a series of raw data via prompting LLMs, filtered with frequency and semantics. Given a new entity that needs tagging for distribution, TagGPT introduces two alternative options for zero-shot tagging, i.e., a generative method with late semantic matching with the tag set, and another selective method with early matching in prompts. It is well noticed that TagGPT provides a system-level solution based on a modular framework equipped with a pre-trained LLM (GPT-3.5 used here) and a sentence embedding model (SimCSE used here), which can be seamlessly replaced with any more advanced one you want. TagGPT is applicable for various modalities of data in modern social media and showcases strong generalization ability to a wide range of applications. We evaluate TagGPT on publicly available datasets, i.e., Kuaishou and Food.com, and demonstrate the effectiveness of TagGPT compared to existing hashtags and off-the-shelf taggers. Project page: https://github.com/TencentARC/TagGPT.

cs.IR↗

arXiv2023

RILS: Masked Visual Reconstruction in Language Semantic Space

Both masked image modeling (MIM) and natural language supervision have facilitated the progress of transferable visual pre-training. In this work, we seek the synergy between two paradigms and study the emerging properties when MIM meets natural language supervision. To this end, we present a novel masked visual Reconstruction In Language semantic Space (RILS) pre-training framework, in which sentence representations, encoded by the text encoder, serve as prototypes to transform the vision-only signals into patch-sentence probabilities as semantically meaningful MIM reconstruction targets. The vision models can therefore capture useful components with structured information by predicting proper semantic of masked tokens. Better visual representations could, in turn, improve the text encoder via the image-text alignment objective, which is essential for the effective MIM target transformation. Extensive experimental results demonstrate that our method not only enjoys the best of previous MIM and CLIP but also achieves further improvements on various tasks due to their mutual benefits. RILS exhibits advanced transferability on downstream classification, detection, and segmentation, especially for low-shot regimes. Code will be made available at https://github.com/hustvl/RILS.

cs.CV↗

arXiv2023

Masked Image Modeling with Denoising Contrast

Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision dictionary look-up. MIM recently dominates this line of research with state-of-the-art performance on vision Transformers (ViTs), where the core is to enhance the patch-level visual context capturing of the network via denoising auto-encoding mechanism. Rather than tailoring image tokenizers with extra training stages as in previous works, we unleash the great potential of contrastive learning on denoising auto-encoding and introduce a pure MIM method, ConMIM, to produce simple intra-image inter-patch contrastive constraints as the sole learning objectives for masked patch prediction. We further strengthen the denoising mechanism with asymmetric designs, including image perturbations and model progress rates, to improve the network pre-training. ConMIM-pretrained models with various scales achieve competitive results on downstream image classification, semantic segmentation, object detection, and instance segmentation tasks, e.g., on ImageNet-1K classification, we achieve 83.9% top-1 accuracy with ViT-Small and 85.3% with ViT-Base without extra data for pre-training.

cs.CV↗

arXiv2022

CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation

To improve instance-level detection/segmentation performance, existing self-supervised and semi-supervised methods extract either task-unrelated or task-specific training signals from unlabeled data. We show that these two approaches, at the two extreme ends of the task-specificity spectrum, are suboptimal for the task performance. Utilizing too little task-specific training signals causes underfitting to the ground-truth labels of downstream tasks, while the opposite causes overfitting to the ground-truth labels. To this end, we propose a novel Class-Agnostic Semi-Supervised Learning (CA-SSL) framework to achieve a more favorable task-specificity balance in extracting training signals from unlabeled data. CA-SSL has three training stages that act on either ground-truth labels (labeled data) or pseudo labels (unlabeled data). This decoupling strategy avoids the complicated scheme in traditional SSL methods that balances the contributions from both data types. Especially, we introduce a warmup training stage to achieve a more optimal balance in task specificity by ignoring class information in the pseudo labels, while preserving localization training signals. As a result, our warmup model can better avoid underfitting/overfitting when fine-tuned on the ground-truth labels in detection and segmentation tasks. Using 3.6M unlabeled data, we achieve a significant performance gain of 4.7% over ImageNet-pretrained baseline on FCOS object detection. In addition, our warmup model demonstrates excellent transferability to other detection and segmentation frameworks.

cs.CV↗

arXiv2022

Controllable Augmentations for Video Representation Learning

This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to bias to static background and have difficulty establishing global temporal structures. The major reason is that the positive pairs, i.e., different clips sampled from the same video, have limited temporal receptive field, and usually share similar background but differ in motions. To address these problems, we propose a framework to jointly utilize local clips and global videos to learn from detailed region-level correspondence as well as general long-term temporal relations. Based on a set of controllable augmentations, we achieve accurate appearance and motion pattern alignment through soft spatio-temporal region contrast. Our formulation is able to avoid the low-level redundancy shortcut by mutual information minimization to improve the generalization. We also introduce local-global temporal order dependency to further bridge the gap between clip-level and video-level representations for robust temporal modeling. Extensive experiments demonstrate that our framework is superior on three video benchmarks in action recognition and video retrieval, capturing more accurate temporal dynamics.

cs.CV↗

arXiv2022

Bridging Video-text Retrieval with Multiple Choice Questions

Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separate encoders for efficient retrieval, but ignore local associations between videos and texts. Another line of research uses a joint encoder to interact video with texts, but results in low efficiency since each text-video pair needs to be fed into the model. In this work, we enable fine-grained video-text interactions while maintaining high efficiency for retrieval via a novel pretext task, dubbed as Multiple Choice Questions (MCQ), where a parametric module BridgeFormer is trained to answer the "questions" constructed by the text features via resorting to the video features. Specifically, we exploit the rich semantics of text (i.e., nouns and verbs) to build questions, with which the video encoder can be trained to capture more regional content and temporal dynamics. In the form of questions and answers, the semantic associations between local video-text features can be properly established. BridgeFormer is able to be removed for downstream retrieval, rendering an efficient and flexible model with only two encoders. Our method outperforms state-of-the-art methods on the popular text-to-video retrieval task in five datasets with different experimental setups (i.e., zero-shot and fine-tune), including HowTo100M (one million videos). We further conduct zero-shot action recognition, which can be cast as video-to-text retrieval, and our approach also significantly surpasses its counterparts. As an additional benefit, our method achieves competitive results with much shorter pre-training videos on single-modality downstream tasks, e.g., action recognition with linear evaluation.

cs.CV↗

arXiv2022

A Two-phase Recommendation Framework for Consistent Java Method Names

In software engineering (SE) tasks, the naming approach is so important that it attracts many scholars from all over the world to study how to improve the quality of method names. To accurately recommend method names, we employ a novel framework to handle this problem. In our expeirments, nearly 8 million Java methods are collected from open source organizations as our evaluation dataset. In the first-phase recommendation, we introduce a fast and simple classifier based on the fast text neural network for reccomending potential method category. In the second-phase recomendation, we employ both two Long Short Term Memory Networks to reccomend consitent method names from each classification. Evaluation results prove that the proposed approach significantly outperforms state-of-the-art approach.

cs.SE↗

arXiv2022

An empirical study on Java method name suggestion: are we there yet?

A large-scale evaluation for current naming approaches substantiates that such approaches are accurate. However, it is less known about which categories of method names work well via such naming approaches and how's the performance of naming approaches. To point out the superiority of the current naming approach, in this paper, we conduct an empirical study on such approaches in a new dataset. Moreover, we analyze the successful naming approaches above and find that: (1) around 60% of the accepted recommendation names are made on prefixes within get, set, is, and test. (2) A large portion (19.3%) of method names successfully recommended could be derived from the given method bodies. The comparisons also demonstrate the superior performance of the empirical study.

cs.SE↗

arXiv2021

CLIP4Caption ++: Multi-CLIP for Video Caption

This report describes our solution to the VALUE Challenge 2021 in the captioning task. Our solution, named CLIP4Caption++, is built on X-Linear/X-Transformer, which is an advanced model with encoder-decoder architecture. We make the following improvements on the proposed CLIP4Caption++: We employ an advanced encoder-decoder model architecture X-Transformer as our main framework and make the following improvements: 1) we utilize three strong pre-trained CLIP models to extract the text-related appearance visual features. 2) we adopt the TSN sampling strategy for data enhancement. 3) we involve the video subtitle information to provide richer semantic information. 3) we introduce the subtitle information, which fuses with the visual features as guidance. 4) we design word-level and sentence-level ensemble strategies. Our proposed method achieves 86.5, 148.4, 64.5 CIDEr scores on VATEX, YC2C, and TVC datasets, respectively, which shows the superior performance of our proposed CLIP4Caption++ on all three datasets.

cs.CV↗

arXiv2021

CLIP4Caption: CLIP for Video Caption

Video captioning is a challenging task since it requires generating sentences describing various diverse and complex videos. Existing video captioning models lack adequate visual representation due to the neglect of the existence of gaps between videos and texts. To bridge this gap, in this paper, we propose a CLIP4Caption framework that improves video captioning based on a CLIP-enhanced video-text matching network (VTM). This framework is taking full advantage of the information from both vision and language and enforcing the model to learn strongly text-correlated video features for text generation. Besides, unlike most existing models using LSTM or GRU as the sentence decoder, we adopt a Transformer structured decoder network to effectively learn the long-range visual and language dependency. Additionally, we introduce a novel ensemble strategy for captioning tasks. Experimental results demonstrate the effectiveness of our method on two datasets: 1) on MSR-VTT dataset, our method achieved a new state-of-the-art result with a significant gain of up to 10% in CIDEr; 2) on the private test data, our method ranking 2nd place in the ACM MM multimedia grand challenge 2021: Pre-training for Video Understanding Challenge. It is noted that our model is only trained on the MSR-VTT dataset.

cs.CV↗

arXiv2021

Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization

The crux of self-supervised video representation learning is to build general features from unlabeled videos. However, most recent works have mainly focused on high-level semantics and neglected lower-level representations and their temporal relationship which are crucial for general video understanding. To address these challenges, this paper proposes a multi-level feature optimization framework to improve the generalization and temporal modeling ability of learned video representations. Concretely, high-level features obtained from naive and prototypical contrastive learning are utilized to build distribution graphs, guiding the process of low-level and mid-level feature learning. We also devise a simple temporal modeling module from multi-level features to enhance motion pattern learning. Experiments demonstrate that multi-level feature optimization with the graph constraint and temporal modeling can greatly improve the representation ability in video understanding. Code is available at https://github.com/shvdiwnkozbw/Video-Representation-via-Multi-level-Optimization.

cs.CV↗

arXiv2021

Ferromagnetism in 2D Vanadium Diselenide

Two-dimensional (2D) Van der Waals ferromagnets carry the promise of ultimately miniature spintronics and information storage devices. Among the newly discovered 2D ferromagnets all inherit the magnetic ordering from their bulk ancestors. Here we report a new 2D ferromagnetic semiconductor at room temperature, 2H phase vanadium diselenide (VSe2) which show ferromagnetic at 2D form only. This unique 2D ferromagnetic semiconductor manifests an enhanced magnetic ordering owing to structural anisotropy at 2D limit.

cond-mat.mtrl-sci↗

arXiv2016

Long valley lifetime of free carriers in monolayer WSe2

Monolayer transition metal dichalcogenids (TMDs) feature valley degree of freedom, giant spin-orbit coupling and spin-valley locking. These exotic natures stimulate efforts of exploring the potential applications in conceptual spintronics, valleytronics and quantum computing. Among all the exotic directions, a long lifetime of spin and/or valley polarization is critical. The present valley dynamics studies concentrate on the band edge excitons which predominates the optical response due to the enhanced Coulomb interaction in two dimensions. The valley lifetime of free carriers remains in ambiguity. In this work, we use time-resolved Kerr rotation spectroscopy to probe the valley dynamics of excitons and free carriers in monolayer tungsten diselinide. The valley lifetime of free carriers is found around 2 ns at 70 K, about 3 orders of magnitude longer than the excitons of about 2 ps. The extended valley lifetime of free carriers evidences that exchange interaction dominates the valley relaxation in optical excitation. The pump-probe spectroscopy also reveals the exciton binding energy of 0.60 eV in monolayer WSe2.

cond-mat.mes-hall↗

arXiv2016

Bound exciton and free exciton states in GaSe thin slab

The photoluminescence (PL) and absorption experiments have been performed in GaSe slab with incident light polarized perpendicular to c-axis of sample at 10K. An obvious energy difference of about 34meV between exciton absorption peak and PL peak (the highest energy peak) is observed. By studying the temperature dependence of PL spectra, we attribute it to energy difference between free exciton and bound exciton states, where main exciton absorption peak comes from free exciton absorption, and PL peak are attributed to recombination of bound exciton at 10K. This strong bound exciton effect is stable up to 50K. Moreover, the temperature dependence of integrated PL intensity and PL lifetime reveals that a non-radiative process, with active energy extracted as 0.5meV, dominates PL emission.

cond-mat.mes-hall↗