arXiv subjects

Hailin Jin

Publications and source records attributed to Hailin Jin.

At least 19 recordsLinked to original sources

arXiv2026

Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers

Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibitive. We introduce Chimera, a hybrid visual diffusion backbone with a principled scaling recipe. Chimera processes text, image, and video tokens in one raster-ordered stream without positional embeddings. It combines Kimi Delta Attention (KDA) for long-context state tracking with O(N) complexity, interleaved Multi-head Latent Attention (MLA) for direct global interaction, and modality-aware short convolutions for local spatiotemporal context. Sparse Mixture-of-Experts (MoE) layers expand capacity while controlling activated compute. To scale this heterogeneous architecture, we introduce HeteroP, a module-wise scheme that transfers hyperparameters across width and depth according to each tensor's functional fan-in and model depth. HeteroP yields a consistently tuned family used to fit Chinchilla-style compute-optimal laws for activated model size, training-token count, and image-video data ratio. Guided by these laws, we train an 11B-parameter Chimera with 2B activated parameters. Experiments show three results. First, measured by pretraining diffusion loss, the dense backbone is 1.7x as compute-efficient as a matched full-attention Wan-2.1 2B baseline, while the complete system reaches 7.3x. Second, without length-specific fine-tuning, Chimera extrapolates zero-shot from 5-second training clips to 30-second videos, with only 6.5% FID degradation in the last five seconds. Third, the fitted laws show that compute-optimal image pretraining divides compute nearly evenly between activated model size and training-token count, whereas video pretraining modestly favors model size at higher budgets. These results establish a foundation for designing and scaling efficient long-context diffusion architectures.

cs.CV↗

arXiv2025

Generative Video Diffusion for Unseen Novel Semantic Video Moment Retrieval

Video moment retrieval (VMR) aims to locate the most likely video moment(s) corresponding to a text query in untrimmed videos. Training of existing methods is limited by the lack of diverse and generalisable VMR datasets, hindering their ability to generalise moment-text associations to queries containing novel semantic concepts (unseen both visually and textually in a training source domain). For model generalisation to novel semantics, existing methods rely heavily on assuming to have access to both video and text sentence pairs from a target domain in addition to the source domain pair-wise training data. This is neither practical nor scalable. In this work, we introduce a more generalisable approach by assuming only text sentences describing new semantics are available in model training without having seen any videos from a target domain. To that end, we propose a Fine-grained Video Editing framework, termed FVE, that explores generative video diffusion to facilitate fine-grained video editing from the seen source concepts to the unseen target sentences consisting of new concepts. This enables generative hypotheses of unseen video moments corresponding to the novel concepts in the target domain. This fine-grained generative video diffusion retains the original video structure and subject specifics from the source domain while introducing semantic distinctions of unseen novel vocabularies in the target domain. A critical challenge is how to enable this generative fine-grained diffusion process to be meaningful in optimising VMR, more than just synthesising visually pleasing videos. We solve this problem by introducing a hybrid selection mechanism that integrates three quantitative metrics to selectively incorporate synthetic video moments (novel video hypotheses) as enlarged additions to the original source training data, whilst minimising potential ...

cs.CV↗

arXiv2024

MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval

Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically matches with a fraction of the prominent video content in the foreground with limited wording diversity. This intrinsic modality imbalance leaves a considerable portion of visual information remaining unaligned with text. It confines the cross-modal alignment knowledge within the scope of a limited text corpus, thereby leading to sub-optimal visual-textual modeling and poor generalizability. By leveraging the visual-textual understanding capability of multi-modal large language models (MLLM), in this work, we take an MLLM as a video narrator to generate plausible textual descriptions of the video, thereby mitigating the modality imbalance and boosting the temporal localization. To effectively maintain temporal sensibility for localization, we design to get text narratives for each certain video timestamp and construct a structured text paragraph with time information, which is temporally aligned with the visual content. Then we perform cross-modal feature merging between the temporal-aware narratives and corresponding video temporal features to produce semantic-enhanced video representation sequences for query localization. Subsequently, we introduce a uni-modal narrative-query matching mechanism, which encourages the model to extract complementary information from contextual cohesive descriptions for improved retrieval. Extensive experiments on two benchmarks show the effectiveness and generalizability of our proposed method.

cs.CV↗

arXiv2023

Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory

Human Object Interaction (HOI) detection aims to localize and infer the relationships between a human and an object. Arguably, training supervised models for this task from scratch presents challenges due to the performance drop over rare classes and the high computational cost and time required to handle long-tailed distributions of HOIs in complex HOI scenes in realistic settings. This observation motivates us to design an HOI detector that can be trained even with long-tailed labeled data and can leverage existing knowledge from pre-trained models. Inspired by the powerful generalization ability of the large Vision-Language Models (VLM) on classification and retrieval tasks, we propose an efficient Adaptive HOI Detector with Concept-guided Memory (ADA-CM). ADA-CM has two operating modes. The first mode makes it tunable without learning new parameters in a training-free paradigm. Its second mode incorporates an instance-aware adapter mechanism that can further efficiently boost performance if updating a lightweight set of parameters can be afforded. Our proposed method achieves competitive results with state-of-the-art on the HICO-DET and V-COCO datasets with much less training time. Code can be found at https://github.com/ltttpku/ADA-CM.

cs.CV↗

arXiv2023

Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models

Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are likely either biased when derived from a limited amount of moment-text data which is hard to scale up because of the prohibitive annotation cost (fully-supervised), or unreliable when only the video-text pairwise relationships are available without fine-grained temporal annotations (weakly-supervised). Recently, the vision-language models (VLM) demonstrate a new transfer learning paradigm to benefit different vision tasks through the universal visual-textual correlations derived from large-scale vision-language pairwise web data, which has also shown benefits to VMR by fine-tuning in the target domains. In this work, we propose a zero-shot method for adapting generalisable visual-textual priors from arbitrary VLM to facilitate moment-text alignment, without the need for accessing the VMR data. To this end, we devise a conditional feature refinement module to generate boundary-aware visual features conditioned on text queries to enable better moment boundary understanding. Additionally, we design a bottom-up proposal generation strategy that mitigates the impact of domain discrepancies and breaks down complex-query retrieval tasks into individual action retrievals, thereby maximizing the benefits of VLM. Extensive experiments conducted on three VMR benchmark datasets demonstrate the notable performance advantages of our zero-shot algorithm, especially in the novel-word and novel-location out-of-distribution setups.

cs.CV↗

arXiv2023

Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training

The correlation between the vision and text is essential for video moment retrieval (VMR), however, existing methods heavily rely on separate pre-training feature extractors for visual and textual understanding. Without sufficient temporal boundary annotations, it is non-trivial to learn universal video-text alignments. In this work, we explore multi-modal correlations derived from large-scale image-text data to facilitate generalisable VMR. To address the limitations of image-text pre-training models on capturing the video changes, we propose a generic method, referred to as Visual-Dynamic Injection (VDI), to empower the model's understanding of video moments. Whilst existing VMR methods are focusing on building temporal-aware video features, being aware of the text descriptions about the temporal changes is also critical but originally overlooked in pre-training by matching static images with sentences. Therefore, we extract visual context and spatial dynamic information from video frames and explicitly enforce their alignments with the phrases describing video changes (e.g. verb). By doing so, the potentially relevant visual and motion patterns in videos are encoded in the corresponding text embeddings (injected) so to enable more accurate video-text alignments. We conduct extensive experiments on two VMR benchmark datasets (Charades-STA and ActivityNet-Captions) and achieve state-of-the-art performances. Especially, VDI yields notable advantages when being tested on the out-of-distribution splits where the testing samples involve novel scenes and vocabulary.

cs.CV↗

arXiv2022

LiveSeg: Unsupervised Multimodal Temporal Segmentation of Long Livestream Videos

Livestream videos have become a significant part of online learning, where design, digital marketing, creative painting, and other skills are taught by experienced experts in the sessions, making them valuable materials. However, Livestream tutorial videos are usually hours long, recorded, and uploaded to the Internet directly after the live sessions, making it hard for other people to catch up quickly. An outline will be a beneficial solution, which requires the video to be temporally segmented according to topics. In this work, we introduced a large Livestream video dataset named MultiLive, and formulated the temporal segmentation of the long Livestream videos (TSLLV) task. We propose LiveSeg, an unsupervised Livestream video temporal Segmentation solution, which takes advantage of multimodal features from different domains. Our method achieved a $16.8\%$ F1-score performance improvement compared with the state-of-the-art method.

cs.CV↗

arXiv2022

Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment

Multimedia summarization with multimodal output (MSMO) is a recently explored application in language grounding. It plays an essential role in real-world applications, i.e., automatically generating cover images and titles for news articles or providing introductions to online videos. However, existing methods extract features from the whole video and article and use fusion methods to select the representative one, thus usually ignoring the critical structure and varying semantics. In this work, we propose a Semantics-Consistent Cross-domain Summarization (SCCS) model based on optimal transport alignment with visual and textual segmentation. In specific, our method first decomposes both video and article into segments in order to capture the structural semantics, respectively. Then SCCS follows a cross-domain alignment objective with optimal transport distance, which leverages multimodal interaction to match and select the visual and textual summary. We evaluated our method on three recent multimodal datasets and demonstrated the effectiveness of our method in producing high-quality multimodal summaries.

cs.CV↗

arXiv2022

Video Activity Localisation with Uncertainties in Temporal Boundary

Current methods for video activity localisation over time assume implicitly that activity temporal boundaries labelled for model training are determined and precise. However, in unscripted natural videos, different activities mostly transit smoothly, so that it is intrinsically ambiguous to determine in labelling precisely when an activity starts and ends over time. Such uncertainties in temporal labelling are currently ignored in model training, resulting in learning mis-matched video-text correlation with poor generalisation in test. In this work, we solve this problem by introducing Elastic Moment Bounding (EMB) to accommodate flexible and adaptive activity temporal boundaries towards modelling universally interpretable video-text correlation with tolerance to underlying temporal uncertainties in pre-fixed annotations. Specifically, we construct elastic boundaries adaptively by mining and discovering frame-wise temporal endpoints that can maximise the alignment between video segments and query sentences. To enable both more accurate matching (segment content attention) and more robust localisation (segment elastic boundaries), we optimise the selection of frame-wise endpoints subject to segment-wise contents by a novel Guided Attention mechanism. Extensive experiments on three video activity localisation benchmarks demonstrate compellingly the EMB's advantages over existing methods without modelling uncertainty.

cs.CV↗

arXiv2022

Cross Modal Retrieval with Querybank Normalisation

Profiting from large-scale training datasets, advances in neural architecture design and efficient inference, joint embeddings have become the dominant approach for tackling cross-modal retrieval. In this work we first show that, despite their effectiveness, state-of-the-art joint embeddings suffer significantly from the longstanding "hubness problem" in which a small number of gallery embeddings form the nearest neighbours of many queries. Drawing inspiration from the NLP literature, we formulate a simple but effective framework called Querybank Normalisation (QB-Norm) that re-normalises query similarities to account for hubs in the embedding space. QB-Norm improves retrieval performance without requiring retraining. Differently from prior work, we show that QB-Norm works effectively without concurrent access to any test set queries. Within the QB-Norm framework, we also propose a novel similarity normalisation method, the Dynamic Inverted Softmax, that is significantly more robust than existing approaches. We showcase QB-Norm across a range of cross modal retrieval models and benchmarks where it consistently enhances strong baselines beyond the state of the art. Code is available at https://vladbogo.github.io/QB-Norm/.

cs.CV↗

arXiv2022

MHMS: Multimodal Hierarchical Multimedia Summarization

Multimedia summarization with multimodal output can play an essential role in real-world applications, i.e., automatically generating cover images and titles for news articles or providing introductions to online videos. In this work, we propose a multimodal hierarchical multimedia summarization (MHMS) framework by interacting visual and language domains to generate both video and textual summaries. Our MHMS method contains video and textual segmentation and summarization module, respectively. It formulates a cross-domain alignment objective with optimal transport distance which leverages cross-domain interaction to generate the representative keyframe and textual summary. We evaluated MHMS on three recent multimodal datasets and demonstrated the effectiveness of our method in producing high-quality multimodal summaries.

cs.CV↗

arXiv2022

StyleBabel: Artistic Style Tagging and Captioning

We present StyleBabel, a unique open access dataset of natural language captions and free-form tags describing the artistic style of over 135K digital artworks, collected via a novel participatory method from experts studying at specialist art and design schools. StyleBabel was collected via an iterative method, inspired by `Grounded Theory': a qualitative approach that enables annotation while co-evolving a shared language for fine-grained artistic style attribute description. We demonstrate several downstream tasks for StyleBabel, adapting the recent ALADIN architecture for fine-grained style similarity, to train cross-modal embeddings for: 1) free-form tag generation; 2) natural language description of artistic style; 3) fine-grained text search of style. To do so, we extend ALADIN with recent advances in Visual Transformer (ViT) and cross-modal representation learning, achieving a state of the art accuracy in fine-grained style retrieval.

cs.CV↗

arXiv2022

A Multi-Implicit Neural Representation for Fonts

Fonts are ubiquitous across documents and come in a variety of styles. They are either represented in a native vector format or rasterized to produce fixed resolution images. In the first case, the non-standard representation prevents benefiting from latest network architectures for neural representations; while, in the latter case, the rasterized representation, when encoded via networks, results in loss of data fidelity, as font-specific discontinuities like edges and corners are difficult to represent using neural networks. Based on the observation that complex fonts can be represented by a superposition of a set of simpler occupancy functions, we introduce \textit{multi-implicits} to represent fonts as a permutation-invariant set of learned implict functions, without losing features (e.g., edges and corners). However, while multi-implicits locally preserve font features, obtaining supervision in the form of ground truth multi-channel signals is a problem in itself. Instead, we propose how to train such a representation with only local supervision, while the proposed neural architecture directly finds globally consistent multi-implicits for font families. We extensively evaluate the proposed representation for various tasks including reconstruction, interpolation, and synthesis to demonstrate clear advantages with existing alternatives. Additionally, the representation naturally enables glyph completion, wherein a single characteristic font is used to synthesize a whole font family in the target style.

cs.CV↗

arXiv2021

Time-Equivariant Contrastive Video Representation Learning

We introduce a novel self-supervised contrastive learning method to learn representations from unlabelled videos. Existing approaches ignore the specifics of input distortions, e.g., by learning invariance to temporal transformations. Instead, we argue that video representation should preserve video dynamics and reflect temporal manipulations of the input. Therefore, we exploit novel constraints to build representations that are equivariant to temporal transformations and better capture video dynamics. In our method, relative temporal transformations between augmented clips of a video are encoded in a vector and contrasted with other transformation vectors. To support temporal equivariance learning, we additionally propose the self-supervised classification of two clips of a video into 1. overlapping 2. ordered, or 3. unordered. Our experiments show that time-equivariant representations achieve state-of-the-art results in video retrieval and action recognition benchmarks on UCF101, HMDB51, and Diving48.

cs.CV↗

arXiv2021

Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos

We introduce the task of spatially localizing narrated interactions in videos. Key to our approach is the ability to learn to spatially localize interactions with self-supervision on a large corpus of videos with accompanying transcribed narrations. To achieve this goal, we propose a multilayer cross-modal attention network that enables effective optimization of a contrastive loss during training. We introduce a divided strategy that alternates between computing inter- and intra-modal attention across the visual and natural language modalities, which allows effective training via directly contrasting the two modalities' representations. We demonstrate the effectiveness of our approach by self-training on the HowTo100M instructional video dataset and evaluating on a newly collected dataset of localized described interactions in the YouCook2 dataset. We show that our approach outperforms alternative baselines, including shallow co-attention and full cross-modal attention. We also apply our approach to grounding phrases in images with weak supervision on Flickr30K and show that stacking multiple attention layers is effective and, when combined with a word-to-region loss, achieves state of the art on recall-at-one and pointing hand accuracies.

cs.CV↗

arXiv2021

TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval

In recent years, considerable progress on the task of text-video retrieval has been achieved by leveraging large-scale pretraining on visual and audio datasets to construct powerful video encoders. By contrast, despite the natural symmetry, the design of effective algorithms for exploiting large-scale language pretraining remains under-explored. In this work, we are the first to investigate the design of such algorithms and propose a novel generalized distillation method, TeachText, which leverages complementary cues from multiple text encoders to provide an enhanced supervisory signal to the retrieval model. Moreover, we extend our method to video side modalities and show that we can effectively reduce the number of used modalities at test time without compromising performance. Our approach advances the state of the art on several video retrieval benchmarks by a significant margin and adds no computational overhead at test time. Last but not least, we show an effective application of our method for eliminating noise from retrieval datasets. Code and data can be found at https://www.robots.ox.ac.uk/~vgg/research/teachtext/.

cs.CV↗

arXiv2021

StreamHover: Livestream Transcript Summarization and Annotation

With the explosive growth of livestream broadcasting, there is an urgent need for new summarization technology that enables us to create a preview of streamed content and tap into this wealth of knowledge. However, the problem is nontrivial due to the informal nature of spoken language. Further, there has been a shortage of annotated datasets that are necessary for transcript summarization. In this paper, we present StreamHover, a framework for annotating and summarizing livestream transcripts. With a total of over 500 hours of videos annotated with both extractive and abstractive summaries, our benchmark dataset is significantly larger than currently existing annotated corpora. We explore a neural extractive summarization model that leverages vector-quantized variational autoencoder to learn latent vector representations of spoken utterances and identify salient utterances from the transcripts to form summaries. We show that our model generalizes better and improves performance over strong baselines. The results of this study provide an avenue for future research to improve summarization solutions for efficient browsing of livestreams.

cs.CL↗

arXiv2021

Font Completion and Manipulation by Cycling Between Multi-Modality Representations

Generating font glyphs of consistent style from one or a few reference glyphs, i.e., font completion, is an important task in topographical design. As the problem is more well-defined than general image style transfer tasks, thus it has received interest from both vision and machine learning communities. Existing approaches address this problem as a direct image-to-image translation task. In this work, we innovate to explore the generation of font glyphs as 2D graphic objects with the graph as an intermediate representation, so that more intrinsic graphic properties of font styles can be captured. Specifically, we formulate a cross-modality cycled image-to-image model structure with a graph constructor between an image encoder and an image renderer. The novel graph constructor maps a glyph's latent code to its graph representation that matches expert knowledge, which is trained to help the translation task. Our model generates improved results than both image-to-image baseline and previous state-of-the-art methods for glyph completion. Furthermore, the graph representation output by our model also provides an intuitive interface for users to do local editing and manipulation. Our proposed cross-modality cycled representation learning has the potential to be applied to other domains with prior knowledge from different data modalities. Our code is available at https://github.com/VITA-Group/Font_Completion_Graph.

cs.CV↗