Junfu Pu

Jiashuo Yu, Junfu Pu, Ying Cheng et al.

Although audio-visual representation has been proved to be applicable in many downstream tasks, the representation of dancing videos, which is more specific and always accompanied by music with complex auditory contents, remains challenging and uninvestigated. Considering the intrinsic alignment between the cadent movement of dancer and music rhythm, we introduce MuDaR, a novel Music-Dance Representation learning framework to perform the synchronization of music and dance rhythms both in explicit and implicit ways. Specifically, we derive the dance rhythms based on visual appearance and motion cues inspired by the music rhythm analysis. Then the visual rhythms are temporally aligned with the music counterparts, which are extracted by the amplitude of sound intensity. Meanwhile, we exploit the implicit coherence of rhythms implied in audio and visual streams by contrastive learning. The model learns the joint embedding by predicting the temporal consistency between audio-visual pairs. The music-dance representation, together with the capability of detecting audio and visual rhythms, can further be applied to three downstream tasks: (a) dance classification, (b) music-dance retrieval, and (c) music-dance retargeting. Extensive experiments demonstrate that our proposed framework outperforms other self-supervised methods by a large margin.

Junfu Pu, Ying Shan

In this paper, we propose a novel framework for music-driven dance motion synthesis with controllable key pose constraint. In contrast to methods that generate dance motion sequences only based on music without any other controllable conditions, this work targets on synthesizing high-quality dance motion driven by music as well as customized poses performed by users. Our model involves two single-modal transformer encoders for music and motion representations and a cross-modal transformer decoder for dance motions generation. The cross-modal transformer decoder achieves the capability of synthesizing smooth dance motion sequences, which keeps a consistency with key poses at corresponding positions, by introducing the local neighbor position embedding. Such mechanism makes the decoder more sensitive to key poses and the corresponding positions. Our dance synthesis model achieves satisfactory performance both on quantitative and qualitative evaluations with extensive experiments, which demonstrates the effectiveness of our proposed method.

Yuxin Chen, Zongyang Ma, Ziqi Zhang et al.

Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from cross-encoder to dual-encoder provides a natural approach to harness their strengths. Thus we investigate the following valuable question: how to make cross-encoder a good teacher for dual-encoder? Our findings are threefold:(1) Cross-modal similarity score distribution of cross-encoder is more concentrated while the result of dual-encoder is nearly normal making vanilla logit distillation less effective. However ranking distillation remains practical as it is not affected by the score distribution.(2) Only the relative order between hard negatives conveys valid knowledge while the order information between easy negatives has little significance.(3) Maintaining the coordination between distillation loss and dual-encoder training loss is beneficial for knowledge transfer. Based on these findings we propose a novel Contrastive Partial Ranking Distillation (CPRD) method which implements the objective of mimicking relative order between hard negative samples with contrastive learning. This approach coordinates with the training of the dual-encoder effectively transferring valid knowledge from the cross-encoder to the dual-encoder. Extensive experiments on image-text retrieval and ranking tasks show that our method surpasses other distillation methods and significantly improves the accuracy of dual-encoder.

Tao Zhang, Ziqi Zhang, Zongyang Ma et al.

Advanced Multimodal Large Language Models (MLLMs) struggle with recent Knowledge-based VQA tasks, such as INFOSEEK and Encyclopedic-VQA, due to their limited and frozen knowledge scope, often leading to ambiguous and inaccurate responses. Thus, multimodal Retrieval-Augmented Generation (mRAG) is naturally introduced to provide MLLMs with comprehensive and up-to-date knowledge, effectively expanding the knowledge scope. However, current mRAG methods have inherent drawbacks, including: 1) Performing retrieval even when external knowledge is not needed. 2) Lacking of identification of evidence that supports the query. 3) Increasing model complexity due to additional information filtering modules or rules. To address these shortcomings, we propose a novel generalized framework called \textbf{m}ultimodal \textbf{R}etrieval-\textbf{R}eflection-\textbf{A}ugmented \textbf{G}eneration (mR$^2$AG), which achieves adaptive retrieval and useful information localization to enable answers through two easy-to-implement reflection operations, preventing high model complexity. In mR$^2$AG, Retrieval-Reflection is designed to distinguish different user queries and avoids redundant retrieval calls, and Relevance-Reflection is introduced to guide the MLLM in locating beneficial evidence of the retrieved content and generating answers accordingly. In addition, mR$^2$AG can be integrated into any well-trained MLLM with efficient fine-tuning on the proposed mR$^2$AG Instruction-Tuning dataset (mR$^2$AG-IT). mR$^2$AG significantly outperforms state-of-the-art MLLMs (e.g., GPT-4v/o) and RAG-based MLLMs on INFOSEEK and Encyclopedic-VQA, while maintaining the exceptional capabilities of base MLLMs across a wide range of Visual-dependent tasks.

Ye Liu, Zongyang Ma, Junfu Pu et al.

Recent advances in Large Multi-modal Models (LMMs) have demonstrated their remarkable success as general-purpose multi-modal assistants, with particular focuses on holistic image- and video-language understanding. Conversely, less attention has been given to scaling fine-grained pixel-level understanding capabilities, where the models are expected to realize pixel-level alignment between visual signals and language semantics. Some previous studies have applied LMMs to related tasks such as region-level captioning and referring expression segmentation. However, these models are limited to performing either referring or segmentation tasks independently and fail to integrate these fine-grained perception capabilities into visual reasoning. To bridge this gap, we propose UniPixel, a large multi-modal model capable of flexibly comprehending visual prompt inputs and generating mask-grounded responses. Our model distinguishes itself by seamlessly integrating pixel-level perception with general visual understanding capabilities. Specifically, UniPixel processes visual prompts and generates relevant masks on demand, and performs subsequent reasoning conditioning on these intermediate pointers during inference, thereby enabling fine-grained pixel-level reasoning. The effectiveness of our approach has been verified on 10 benchmarks across a diverse set of tasks, including pixel-level referring/segmentation and object-centric understanding in images/videos. A novel PixelQA task that jointly requires referring, segmentation, and question answering is also designed to verify the flexibility of our method.

Zehao Wang, Xinpeng Liu, Xiaoqian Wu et al.

Multimodal Large Language Models (MLLMs) have garnered significant attention recently and demonstrate outstanding capabilities in various tasks such as OCR, VQA, captioning, $\textit{etc}$. However, hallucination remains a persistent issue. While numerous methods have been proposed to mitigate hallucinations, achieving notable improvements, these methods primarily focus on mitigating hallucinations about $\textbf{object/noun-related}$ concepts. Verb concepts, crucial for understanding human actions, have been largely overlooked. In this paper, to the best of our knowledge, we are the $\textbf{first}$ to investigate the $\textbf{verb hallucination}$ phenomenon of MLLMs from various perspectives. Our findings reveal that most state-of-the-art MLLMs suffer from severe verb hallucination. To assess the effectiveness of existing mitigation methods for object concept hallucination on verb hallucination, we evaluated these methods and found that they do not effectively address verb hallucination. To address this issue, we propose a novel rich verb knowledge-based tuning method to mitigate verb hallucination. The experiment results demonstrate that our method significantly reduces hallucinations related to verbs.

Hao Zhou, Wengang Zhou, Weizhen Qi et al.

Despite existing pioneering works on sign language translation (SLT), there is a non-trivial obstacle, i.e., the limited quantity of parallel sign-text data. To tackle this parallel data bottleneck, we propose a sign back-translation (SignBT) approach, which incorporates massive spoken language texts into SLT training. With a text-to-gloss translation model, we first back-translate the monolingual text to its gloss sequence. Then, the paired sign sequence is generated by splicing pieces from an estimated gloss-to-sign bank at the feature level. Finally, the synthetic parallel data serves as a strong supplement for the end-to-end training of the encoder-decoder SLT framework. To promote the SLT research, we further contribute CSL-Daily, a large-scale continuous SLT dataset. It provides both spoken language translations and gloss-level annotations. The topic revolves around people's daily lives (e.g., travel, shopping, medical care), the most likely SLT application scenario. Extensive experimental results and analysis of SLT methods are reported on CSL-Daily. With the proposed sign back-translation method, we obtain a substantial improvement over previous state-of-the-art SLT methods.

Junfu Pu, Wengang Zhou, Hezhen Hu et al.

Continuous sign language recognition (SLR) deals with unaligned video-text pair and uses the word error rate (WER), i.e., edit distance, as the main evaluation metric. Since it is not differentiable, we usually instead optimize the learning model with the connectionist temporal classification (CTC) objective loss, which maximizes the posterior probability over the sequential alignment. Due to the optimization gap, the predicted sentence with the highest decoding probability may not be the best choice under the WER metric. To tackle this issue, we propose a novel architecture with cross modality augmentation. Specifically, we first augment cross-modal data by simulating the calculation procedure of WER, i.e., substitution, deletion and insertion on both text label and its corresponding video. With these real and generated pseudo video-text pairs, we propose multiple loss terms to minimize the cross modality distance between the video and ground truth label, and make the network distinguish the difference between real and pseudo modalities. The proposed framework can be easily extended to other existing CTC based continuous SLR architectures. Extensive experiments on two continuous SLR benchmarks, i.e., RWTH-PHOENIX-Weather and CSL, validate the effectiveness of our proposed method.