Rebalancing Contrastive Alignment with Learnable Semantic Gaps in Text-Video Retrieval

Recent advances in text-video retrieval have been largely driven by contrastive learning frameworks. However, existing methods overlook a key source of optimization tension: the separation between text and video distributions in the representation space (referred to as the modality gap), and the prevalence of false negatives in batch sampling. These factors lead to conflicting gradients under the InfoNCE loss, impeding stable alignment. To mitigate this, we propose GARE, a Gap-Aware Retrieval framework that introduces a learnable, pair-specific increment Delta_ij between text t_i and video v_j to offload the tension from the global anchor representation. We first derive the ideal form of Delta_ij via a coupled multivariate first-order Taylor approximation of the InfoNCE loss under a trust-region constraint, revealing it as a mechanism for resolving gradient conflicts by guiding updates along a locally optimal descent direction. Due to the high cost of directly computing Delta_ij, we introduce a lightweight neural module conditioned on the semantic gap between each video-text pair, enabling structure-aware correction guided by gradient supervision. To further stabilize learning and promote interpretability, we regularize Delta using three components: a trust-region constraint to prevent oscillation, a directional diversity term to promote semantic coverage, and an information bottleneck to limit redundancy. Experiments across four retrieval benchmarks show that GARE consistently improves alignment accuracy and robustness to noisy supervision, confirming the effectiveness of gap-aware tension mitigation.

Concept Drift Guided LayerNorm Tuning for Efficient Multimodal Metaphor Identification

Metaphorical imagination, the ability to connect seemingly unrelated concepts, is fundamental to human cognition and communication. While understanding linguistic metaphors has advanced significantly, grasping multimodal metaphors, such as those found in internet memes, presents unique challenges due to their unconventional expressions and implied meanings. Existing methods for multimodal metaphor identification often struggle to bridge the gap between literal and figurative interpretations. Additionally, generative approaches that utilize large language models or text-to-image models, while promising, suffer from high computational costs. This paper introduces \textbf{C}oncept \textbf{D}rift \textbf{G}uided \textbf{L}ayerNorm \textbf{T}uning (\textbf{CDGLT}), a novel and training-efficient framework for multimodal metaphor identification. CDGLT incorporates two key innovations: (1) Concept Drift, a mechanism that leverages Spherical Linear Interpolation (SLERP) of cross-modal embeddings from a CLIP encoder to generate a new, divergent concept embedding. This drifted concept helps to alleviate the gap between literal features and the figurative task. (2) A prompt construction strategy, that adapts the method of feature extraction and fusion using pre-trained language models for the multimodal metaphor identification task. CDGLT achieves state-of-the-art performance on the MET-Meme benchmark while significantly reducing training costs compared to existing generative methods. Ablation studies demonstrate the effectiveness of both Concept Drift and our adapted LN Tuning approach. Our method represents a significant step towards efficient and accurate multimodal metaphor understanding. The code is available: \href{https://github.com/Qianvenh/CDGLT}{https://github.com/Qianvenh/CDGLT}.

Video Flow as Time Series: Discovering Temporal Consistency and Variability for VideoQA

Video Question Answering (VideoQA) is a complex video-language task that demands a sophisticated understanding of both visual content and temporal dynamics. Traditional Transformer-style architectures, while effective in integrating multimodal data, often simplify temporal dynamics through positional encoding and fail to capture non-linear interactions within video sequences. In this paper, we introduce the Temporal Trio Transformer (T3T), a novel architecture that models time consistency and time variability. The T3T integrates three key components: Temporal Smoothing (TS), Temporal Difference (TD), and Temporal Fusion (TF). The TS module employs Brownian Bridge for capturing smooth, continuous temporal transitions, while the TD module identifies and encodes significant temporal variations and abrupt changes within the video content. Subsequently, the TF module synthesizes these temporal features with textual cues, facilitating a deeper contextual understanding and response accuracy. The efficacy of the T3T is demonstrated through extensive testing on multiple VideoQA benchmark datasets. Our results underscore the importance of a nuanced approach to temporal modeling in improving the accuracy and depth of video-based question answering.

Grid Jigsaw Representation with CLIP: A New Perspective on Image Clustering

Unsupervised representation learning for image clustering is essential in computer vision. Although the advancement of visual models has improved image clustering with efficient visual representations, challenges still remain. Firstly, these features often lack the ability to represent the internal structure of images, hindering the accurate clustering of visually similar images. Secondly, the existing features tend to lack finer-grained semantic labels, limiting the ability to capture nuanced differences and similarities between images. In this paper, we first introduce Jigsaw based strategy method for image clustering called Grid Jigsaw Representation (GJR) with systematic exposition from pixel to feature in discrepancy against human and computer. We emphasize that this algorithm, which mimics human jigsaw puzzle, can effectively improve the model to distinguish the spatial feature between different samples and enhance the clustering ability. GJR modules are appended to a variety of deep convolutional networks and tested with significant improvements on a wide range of benchmark datasets including CIFAR-10, CIFAR-100/20, STL-10, ImageNet-10 and ImageNetDog-15. On the other hand, convergence efficiency is always an important challenge for unsupervised image clustering. Recently, pretrained representation learning has made great progress and released models can extract mature visual representations. It is obvious that use the pretrained model as feature extractor can speed up the convergence of clustering where our aim is to provide new perspective in image clustering with reasonable resource application and provide new baseline. Further, we innovate pretrain-based Grid Jigsaw Representation (pGJR) with improvement by GJR. The experiment results show the effectiveness on the clustering task with respect to the ACC, NMI and ARI three metrics and super fast convergence speed.

Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioning

Cross-lingual image captioning is confronted with both cross-lingual and cross-modal challenges for multimedia analysis. The crucial issue in this task is to model the global and local matching between the image and different languages. Existing cross-modal embedding methods based on Transformer architecture oversight the local matching between the image region and monolingual words, not to mention in the face of a variety of differentiated languages. Due to the heterogeneous property of the cross-modal and cross-lingual task, we utilize the heterogeneous network to establish cross-domain relationships and the local correspondences between the image and different languages. In this paper, we propose an Embedded Heterogeneous Attention Transformer (EHAT) to build reasoning paths bridging cross-domain for cross-lingual image captioning and integrate into transformer. The proposed EHAT consists of a Masked Heterogeneous Cross-attention (MHCA), Heterogeneous Attention Reasoning Network (HARN) and Heterogeneous Co-attention (HCA). HARN as the core network, models and infers cross-domain relationship anchored by vision bounding box representation features to connect two languages word features and learn the heterogeneous maps. MHCA and HCA implement cross-domain integration in the encoder through the special heterogeneous attention and enable single model to generate two language captioning. We test on MSCOCO dataset to generate English and Chinese, which are most widely used and have obvious difference between their language families. Our experiments show that our method even achieve better than advanced monolingual methods.