{ "metadata": { "model_name": "ReCo-7B", "model_backbone": "Qwen2-VL-7B-Instruct", "model_size": 8.29, "embedding_dimension": 3584, "max_length_tokens": 4096, "model_release_date": "2025-08-13", "data_source": "Self-Reported", "url": "", "report_generated_date": "2025-08-15T11:46:24.390071" }, "metrics": { "image": { "ImageNet-1K": { "hit@1": 0.842, "hit@5": 0.974, "hit@10": 0.99, "ndcg_linear@1": 0.842, "ndcg_linear@5": 0.9169808568878655, "ndcg_linear@10": 0.9222361526909143, "ndcg_exponential@1": 0.842, "ndcg_exponential@5": 0.9169808568878655, "ndcg_exponential@10": 0.9222361526909143, "precision@1": 0.842, "precision@5": 0.19480000000000003, "precision@10": 0.09900000000000002, "recall@1": 0.842, "recall@5": 0.974, "recall@10": 0.99, "f1@1": 0.842, "f1@5": 0.3246666666666666, "f1@10": 0.17999999999999997, "map@1": 0.842, "map@5": 0.8975833333333334, "map@10": 0.8998019841269841, "mrr@1": 0.842, "mrr@5": 0.8975833333333334, "mrr@10": 0.8998019841269841, "num_pred": 1000, "num_data": 1000 }, "N24News": { "hit@1": 0.838, "hit@5": 0.979, "hit@10": 0.996, "ndcg_linear@1": 0.838, "ndcg_linear@5": 0.9177533233244777, "ndcg_linear@10": 0.9232681015441612, "ndcg_exponential@1": 0.838, "ndcg_exponential@5": 0.9177533233244777, "ndcg_exponential@10": 0.9232681015441612, "precision@1": 0.838, "precision@5": 0.1958, "precision@10": 0.09960000000000002, "recall@1": 0.838, "recall@5": 0.979, "recall@10": 0.996, "f1@1": 0.838, "f1@5": 0.3263333333333333, "f1@10": 0.18109090909090905, "map@1": 0.838, "map@5": 0.8969333333333334, "map@10": 0.8992178571428572, "mrr@1": 0.838, "mrr@5": 0.8969333333333334, "mrr@10": 0.8992178571428572, "num_pred": 1000, "num_data": 1000 }, "HatefulMemes": { "hit@1": 0.736, "hit@5": 1.0, "hit@10": 1.0, "ndcg_linear@1": 0.736, "ndcg_linear@5": 0.9025654549428648, "ndcg_linear@10": 0.9025654549428648, "ndcg_exponential@1": 0.736, "ndcg_exponential@5": 0.9025654549428648, "ndcg_exponential@10": 0.9025654549428648, "precision@1": 0.736, "precision@5": 0.20000000000000004, "precision@10": 0.10000000000000002, "recall@1": 0.736, "recall@5": 1.0, "recall@10": 1.0, "f1@1": 0.736, "f1@5": 0.3333333333333333, "f1@10": 0.18181818181818182, "map@1": 0.736, "map@5": 0.868, "map@10": 0.868, "mrr@1": 0.736, "mrr@5": 0.868, "mrr@10": 0.868, "num_pred": 1000, "num_data": 1000 }, "VOC2007": { "hit@1": 0.888, "hit@5": 0.981, "hit@10": 0.993, "ndcg_linear@1": 0.888, "ndcg_linear@5": 0.9398071066575828, "ndcg_linear@10": 0.9438678705568136, "ndcg_exponential@1": 0.888, "ndcg_exponential@5": 0.9398071066575828, "ndcg_exponential@10": 0.9438678705568136, "precision@1": 0.888, "precision@5": 0.19620000000000004, "precision@10": 0.09930000000000001, "recall@1": 0.888, "recall@5": 0.981, "recall@10": 0.993, "f1@1": 0.888, "f1@5": 0.327, "f1@10": 0.18054545454545454, "map@1": 0.888, "map@5": 0.9259166666666667, "map@10": 0.9276964285714286, "mrr@1": 0.888, "mrr@5": 0.9259166666666667, "mrr@10": 0.9276964285714286, "num_pred": 1000, "num_data": 1000 }, "SUN397": { "hit@1": 0.812, "hit@5": 0.974, "hit@10": 0.993, "ndcg_linear@1": 0.812, "ndcg_linear@5": 0.9050798887216867, "ndcg_linear@10": 0.9113630637757374, "ndcg_exponential@1": 0.812, "ndcg_exponential@5": 0.9050798887216867, "ndcg_exponential@10": 0.9113630637757374, "precision@1": 0.812, "precision@5": 0.1948, "precision@10": 0.09930000000000001, "recall@1": 0.812, "recall@5": 0.974, "recall@10": 0.993, "f1@1": 0.812, "f1@5": 0.3246666666666666, "f1@10": 0.18054545454545454, "map@1": 0.812, "map@5": 0.8815166666666666, "map@10": 0.8841936507936508, "mrr@1": 0.812, "mrr@5": 0.8815166666666666, "mrr@10": 0.8841936507936508, "num_pred": 1000, "num_data": 1000 }, "Place365": { "hit@1": 0.474, "hit@5": 0.768, "hit@10": 0.852, "ndcg_linear@1": 0.474, "ndcg_linear@5": 0.6311046356761877, "ndcg_linear@10": 0.6586553758266658, "ndcg_exponential@1": 0.474, "ndcg_exponential@5": 0.6311046356761877, "ndcg_exponential@10": 0.6586553758266658, "precision@1": 0.474, "precision@5": 0.1536, "precision@10": 0.0852, "recall@1": 0.474, "recall@5": 0.768, "recall@10": 0.852, "f1@1": 0.474, "f1@5": 0.25600000000000006, "f1@10": 0.1549090909090909, "map@1": 0.474, "map@5": 0.5855499999999999, "map@10": 0.5971436507936507, "mrr@1": 0.474, "mrr@5": 0.5855499999999999, "mrr@10": 0.5971436507936507, "num_pred": 1000, "num_data": 1000 }, "ImageNet-A": { "hit@1": 0.583, "hit@5": 0.797, "hit@10": 0.866, "ndcg_linear@1": 0.583, "ndcg_linear@5": 0.6975606813028716, "ndcg_linear@10": 0.7200508815122667, "ndcg_exponential@1": 0.583, "ndcg_exponential@5": 0.6975606813028716, "ndcg_exponential@10": 0.7200508815122667, "precision@1": 0.583, "precision@5": 0.1594, "precision@10": 0.08660000000000001, "recall@1": 0.583, "recall@5": 0.797, "recall@10": 0.866, "f1@1": 0.583, "f1@5": 0.2656666666666667, "f1@10": 0.15745454545454543, "map@1": 0.583, "map@5": 0.6644166666666667, "map@10": 0.6738015873015872, "mrr@1": 0.583, "mrr@5": 0.6644166666666667, "mrr@10": 0.6738015873015872, "num_pred": 1000, "num_data": 1000 }, "ImageNet-R": { "hit@1": 0.901, "hit@5": 0.974, "hit@10": 0.985, "ndcg_linear@1": 0.901, "ndcg_linear@5": 0.9428728164969148, "ndcg_linear@10": 0.9463869207847713, "ndcg_exponential@1": 0.901, "ndcg_exponential@5": 0.9428728164969148, "ndcg_exponential@10": 0.9463869207847713, "precision@1": 0.901, "precision@5": 0.19480000000000003, "precision@10": 0.09850000000000003, "recall@1": 0.901, "recall@5": 0.974, "recall@10": 0.985, "f1@1": 0.901, "f1@5": 0.3246666666666666, "f1@10": 0.17909090909090908, "map@1": 0.901, "map@5": 0.9322333333333334, "map@10": 0.9336595238095238, "mrr@1": 0.901, "mrr@5": 0.9322333333333334, "mrr@10": 0.9336595238095238, "num_pred": 1000, "num_data": 1000 }, "ObjectNet": { "hit@1": 0.741, "hit@5": 0.894, "hit@10": 0.936, "ndcg_linear@1": 0.741, "ndcg_linear@5": 0.8248149282858466, "ndcg_linear@10": 0.8386528186011956, "ndcg_exponential@1": 0.741, "ndcg_exponential@5": 0.8248149282858466, "ndcg_exponential@10": 0.8386528186011956, "precision@1": 0.741, "precision@5": 0.17880000000000001, "precision@10": 0.0936, "recall@1": 0.741, "recall@5": 0.894, "recall@10": 0.936, "f1@1": 0.741, "f1@5": 0.298, "f1@10": 0.17018181818181818, "map@1": 0.741, "map@5": 0.80165, "map@10": 0.807506746031746, "mrr@1": 0.741, "mrr@5": 0.80165, "mrr@10": 0.807506746031746, "num_pred": 1000, "num_data": 1000 }, "Country211": { "hit@1": 0.28, "hit@5": 0.501, "hit@10": 0.593, "ndcg_linear@1": 0.28, "ndcg_linear@5": 0.3967797732574324, "ndcg_linear@10": 0.4266616928392452, "ndcg_exponential@1": 0.28, "ndcg_exponential@5": 0.3967797732574324, "ndcg_exponential@10": 0.4266616928392452, "precision@1": 0.28, "precision@5": 0.10019999999999998, "precision@10": 0.0593, "recall@1": 0.28, "recall@5": 0.501, "recall@10": 0.593, "f1@1": 0.28, "f1@5": 0.16700000000000007, "f1@10": 0.10781818181818184, "map@1": 0.28, "map@5": 0.3621333333333333, "map@10": 0.37453452380952384, "mrr@1": 0.28, "mrr@5": 0.3621333333333333, "mrr@10": 0.37453452380952384, "num_pred": 1000, "num_data": 1000 }, "OK-VQA": { "hit@1": 0.741, "hit@5": 0.948, "hit@10": 0.974, "ndcg_linear@1": 0.741, "ndcg_linear@5": 0.8542799837118041, "ndcg_linear@10": 0.8626570169868899, "ndcg_exponential@1": 0.741, "ndcg_exponential@5": 0.8542799837118041, "ndcg_exponential@10": 0.8626570169868899, "precision@1": 0.741, "precision@5": 0.18960000000000002, "precision@10": 0.0974, "recall@1": 0.741, "recall@5": 0.948, "recall@10": 0.974, "f1@1": 0.741, "f1@5": 0.316, "f1@10": 0.17709090909090908, "map@1": 0.741, "map@5": 0.8228, "map@10": 0.8262361111111111, "mrr@1": 0.741, "mrr@5": 0.8228, "mrr@10": 0.8262361111111111, "num_pred": 1000, "num_data": 1000 }, "A-OKVQA": { "hit@1": 0.618, "hit@5": 0.911, "hit@10": 0.947, "ndcg_linear@1": 0.618, "ndcg_linear@5": 0.7808622188164511, "ndcg_linear@10": 0.7926466350990377, "ndcg_exponential@1": 0.618, "ndcg_exponential@5": 0.7808622188164511, "ndcg_exponential@10": 0.7926466350990377, "precision@1": 0.618, "precision@5": 0.18220000000000003, "precision@10": 0.09470000000000002, "recall@1": 0.618, "recall@5": 0.911, "recall@10": 0.947, "f1@1": 0.618, "f1@5": 0.30366666666666664, "f1@10": 0.17218181818181816, "map@1": 0.618, "map@5": 0.7369666666666667, "map@10": 0.7419150793650793, "mrr@1": 0.618, "mrr@5": 0.7369666666666667, "mrr@10": 0.7419150793650793, "num_pred": 1000, "num_data": 1000 }, "DocVQA": { "hit@1": 0.951, "hit@5": 0.994, "hit@10": 0.998, "ndcg_linear@1": 0.951, "ndcg_linear@5": 0.9764817817885069, "ndcg_linear@10": 0.9777793782087449, "ndcg_exponential@1": 0.951, "ndcg_exponential@5": 0.9764817817885069, "ndcg_exponential@10": 0.9777793782087449, "precision@1": 0.951, "precision@5": 0.1988, "precision@10": 0.09980000000000001, "recall@1": 0.951, "recall@5": 0.994, "recall@10": 0.998, "f1@1": 0.951, "f1@5": 0.3313333333333333, "f1@10": 0.18145454545454545, "map@1": 0.951, "map@5": 0.9704166666666667, "map@10": 0.970952380952381, "mrr@1": 0.951, "mrr@5": 0.9704166666666667, "mrr@10": 0.970952380952381, "num_pred": 1000, "num_data": 1000 }, "InfographicsVQA": { "hit@1": 0.763, "hit@5": 0.929, "hit@10": 0.953, "ndcg_linear@1": 0.763, "ndcg_linear@5": 0.8573018965999305, "ndcg_linear@10": 0.8651464819562541, "ndcg_exponential@1": 0.763, "ndcg_exponential@5": 0.8573018965999305, "ndcg_exponential@10": 0.8651464819562541, "precision@1": 0.763, "precision@5": 0.18580000000000002, "precision@10": 0.09530000000000001, "recall@1": 0.763, "recall@5": 0.929, "recall@10": 0.953, "f1@1": 0.763, "f1@5": 0.3096666666666667, "f1@10": 0.17327272727272724, "map@1": 0.763, "map@5": 0.8329333333333333, "map@10": 0.8362166666666667, "mrr@1": 0.763, "mrr@5": 0.8329333333333333, "mrr@10": 0.8362166666666667, "num_pred": 1000, "num_data": 1000 }, "ChartQA": { "hit@1": 0.667, "hit@5": 0.834, "hit@10": 0.883, "ndcg_linear@1": 0.667, "ndcg_linear@5": 0.7600886613750871, "ndcg_linear@10": 0.7759358605253632, "ndcg_exponential@1": 0.667, "ndcg_exponential@5": 0.7600886613750871, "ndcg_exponential@10": 0.7759358605253632, "precision@1": 0.667, "precision@5": 0.1668, "precision@10": 0.08830000000000002, "recall@1": 0.667, "recall@5": 0.834, "recall@10": 0.883, "f1@1": 0.667, "f1@5": 0.278, "f1@10": 0.16054545454545457, "map@1": 0.667, "map@5": 0.7350999999999999, "map@10": 0.7416428571428572, "mrr@1": 0.667, "mrr@5": 0.7350999999999999, "mrr@10": 0.7416428571428572, "num_pred": 1000, "num_data": 1000 }, "Visual7W": { "hit@1": 0.672, "hit@5": 0.946, "hit@10": 0.978, "ndcg_linear@1": 0.672, "ndcg_linear@5": 0.824228757783037, "ndcg_linear@10": 0.8347907629108037, "ndcg_exponential@1": 0.672, "ndcg_exponential@5": 0.824228757783037, "ndcg_exponential@10": 0.8347907629108037, "precision@1": 0.672, "precision@5": 0.1892, "precision@10": 0.09780000000000001, "recall@1": 0.672, "recall@5": 0.946, "recall@10": 0.978, "f1@1": 0.672, "f1@5": 0.31533333333333335, "f1@10": 0.17781818181818182, "map@1": 0.672, "map@5": 0.7831500000000001, "map@10": 0.7876297619047619, "mrr@1": 0.672, "mrr@5": 0.7831500000000001, "mrr@10": 0.7876297619047619, "num_pred": 1000, "num_data": 1000 }, "ScienceQA": { "hit@1": 0.545, "hit@5": 0.829, "hit@10": 0.914, "ndcg_linear@1": 0.545, "ndcg_linear@5": 0.7030948081748067, "ndcg_linear@10": 0.7303193965724715, "ndcg_exponential@1": 0.545, "ndcg_exponential@5": 0.7030948081748067, "ndcg_exponential@10": 0.7303193965724715, "precision@1": 0.545, "precision@5": 0.1658, "precision@10": 0.09140000000000002, "recall@1": 0.545, "recall@5": 0.829, "recall@10": 0.914, "f1@1": 0.545, "f1@5": 0.2763333333333334, "f1@10": 0.16618181818181818, "map@1": 0.545, "map@5": 0.6605666666666667, "map@10": 0.6716507936507936, "mrr@1": 0.545, "mrr@5": 0.6605666666666667, "mrr@10": 0.6716507936507936, "num_pred": 1000, "num_data": 1000 }, "VizWiz": { "hit@1": 0.554, "hit@5": 0.727, "hit@10": 0.77, "ndcg_linear@1": 0.554, "ndcg_linear@5": 0.6497693506578391, "ndcg_linear@10": 0.6637016532467203, "ndcg_exponential@1": 0.554, "ndcg_exponential@5": 0.6497693506578391, "ndcg_exponential@10": 0.6637016532467203, "precision@1": 0.554, "precision@5": 0.1454, "precision@10": 0.077, "recall@1": 0.554, "recall@5": 0.727, "recall@10": 0.77, "f1@1": 0.554, "f1@5": 0.24233333333333337, "f1@10": 0.14, "map@1": 0.554, "map@5": 0.6237666666666667, "map@10": 0.6295341269841269, "mrr@1": 0.554, "mrr@5": 0.6237666666666667, "mrr@10": 0.6295341269841269, "num_pred": 1000, "num_data": 1000 }, "GQA": { "hit@1": 0.768, "hit@5": 0.92, "hit@10": 0.96, "ndcg_linear@1": 0.768, "ndcg_linear@5": 0.853640743755153, "ndcg_linear@10": 0.8666865042079988, "ndcg_exponential@1": 0.768, "ndcg_exponential@5": 0.853640743755153, "ndcg_exponential@10": 0.8666865042079988, "precision@1": 0.768, "precision@5": 0.184, "precision@10": 0.096, "recall@1": 0.768, "recall@5": 0.92, "recall@10": 0.96, "f1@1": 0.768, "f1@5": 0.30666666666666664, "f1@10": 0.17454545454545453, "map@1": 0.768, "map@5": 0.8311333333333333, "map@10": 0.8365781746031746, "mrr@1": 0.768, "mrr@5": 0.8311333333333333, "mrr@10": 0.8365781746031746, "num_pred": 1000, "num_data": 1000 }, "TextVQA": { "hit@1": 0.873, "hit@5": 0.935, "hit@10": 0.949, "ndcg_linear@1": 0.873, "ndcg_linear@5": 0.9070534528555378, "ndcg_linear@10": 0.9116645331300783, "ndcg_exponential@1": 0.873, "ndcg_exponential@5": 0.9070534528555378, "ndcg_exponential@10": 0.9116645331300783, "precision@1": 0.873, "precision@5": 0.18700000000000003, "precision@10": 0.09490000000000001, "recall@1": 0.873, "recall@5": 0.935, "recall@10": 0.949, "f1@1": 0.873, "f1@5": 0.31166666666666665, "f1@10": 0.17254545454545453, "map@1": 0.873, "map@5": 0.8976833333333334, "map@10": 0.8996337301587303, "mrr@1": 0.873, "mrr@5": 0.8976833333333334, "mrr@10": 0.8996337301587303, "num_pred": 1000, "num_data": 1000 }, "VisDial": { "hit@1": 0.853, "hit@5": 0.972, "hit@10": 0.992, "ndcg_linear@1": 0.853, "ndcg_linear@5": 0.9193705465701587, "ndcg_linear@10": 0.9257226856429019, "ndcg_exponential@1": 0.853, "ndcg_exponential@5": 0.9193705465701587, "ndcg_exponential@10": 0.9257226856429019, "precision@1": 0.853, "precision@5": 0.19440000000000004, "precision@10": 0.09920000000000001, "recall@1": 0.853, "recall@5": 0.972, "recall@10": 0.992, "f1@1": 0.853, "f1@5": 0.324, "f1@10": 0.18036363636363634, "map@1": 0.853, "map@5": 0.9015833333333333, "map@10": 0.9041388888888889, "mrr@1": 0.853, "mrr@5": 0.9015833333333333, "mrr@10": 0.9041388888888889, "num_pred": 1000, "num_data": 1000 }, "CIRR": { "hit@1": 0.607, "hit@5": 0.915, "hit@10": 0.957, "ndcg_linear@1": 0.607, "ndcg_linear@5": 0.7794563710701871, "ndcg_linear@10": 0.7931378154576212, "ndcg_exponential@1": 0.607, "ndcg_exponential@5": 0.7794563710701871, "ndcg_exponential@10": 0.7931378154576212, "precision@1": 0.607, "precision@5": 0.18300000000000002, "precision@10": 0.09570000000000002, "recall@1": 0.607, "recall@5": 0.915, "recall@10": 0.957, "f1@1": 0.607, "f1@5": 0.305, "f1@10": 0.174, "map@1": 0.607, "map@5": 0.7335499999999999, "map@10": 0.7392559523809523, "mrr@1": 0.607, "mrr@5": 0.7335499999999999, "mrr@10": 0.7392559523809523, "num_pred": 1000, "num_data": 1000 }, "VisualNews_t2i": { "hit@1": 0.814, "hit@5": 0.931, "hit@10": 0.953, "ndcg_linear@1": 0.814, "ndcg_linear@5": 0.8773775385467573, "ndcg_linear@10": 0.8846105418065908, "ndcg_exponential@1": 0.814, "ndcg_exponential@5": 0.8773775385467573, "ndcg_exponential@10": 0.8846105418065908, "precision@1": 0.814, "precision@5": 0.1862, "precision@10": 0.09530000000000001, "recall@1": 0.814, "recall@5": 0.931, "recall@10": 0.953, "f1@1": 0.814, "f1@5": 0.31033333333333335, "f1@10": 0.17327272727272724, "map@1": 0.814, "map@5": 0.8594666666666667, "map@10": 0.862522619047619, "mrr@1": 0.814, "mrr@5": 0.8594666666666667, "mrr@10": 0.862522619047619, "num_pred": 1000, "num_data": 1000 }, "VisualNews_i2t": { "hit@1": 0.843, "hit@5": 0.942, "hit@10": 0.962, "ndcg_linear@1": 0.843, "ndcg_linear@5": 0.8979380364111543, "ndcg_linear@10": 0.9045114253977077, "ndcg_exponential@1": 0.843, "ndcg_exponential@5": 0.8979380364111543, "ndcg_exponential@10": 0.9045114253977077, "precision@1": 0.843, "precision@5": 0.18840000000000004, "precision@10": 0.09620000000000002, "recall@1": 0.843, "recall@5": 0.942, "recall@10": 0.962, "f1@1": 0.843, "f1@5": 0.314, "f1@10": 0.17490909090909088, "map@1": 0.843, "map@5": 0.8830833333333332, "map@10": 0.8858559523809523, "mrr@1": 0.843, "mrr@5": 0.8830833333333332, "mrr@10": 0.8858559523809523, "num_pred": 1000, "num_data": 1000 }, "MSCOCO_t2i": { "hit@1": 0.795, "hit@5": 0.956, "hit@10": 0.984, "ndcg_linear@1": 0.795, "ndcg_linear@5": 0.8865164749336064, "ndcg_linear@10": 0.895666012550312, "ndcg_exponential@1": 0.795, "ndcg_exponential@5": 0.8865164749336064, "ndcg_exponential@10": 0.895666012550312, "precision@1": 0.795, "precision@5": 0.19120000000000004, "precision@10": 0.0984, "recall@1": 0.795, "recall@5": 0.956, "recall@10": 0.984, "f1@1": 0.795, "f1@5": 0.31866666666666665, "f1@10": 0.17890909090909088, "map@1": 0.795, "map@5": 0.8628666666666666, "map@10": 0.8667003968253968, "mrr@1": 0.795, "mrr@5": 0.8628666666666666, "mrr@10": 0.8667003968253968, "num_pred": 1000, "num_data": 1000 }, "MSCOCO_i2t": { "hit@1": 0.74, "hit@5": 0.937, "hit@10": 0.971, "ndcg_linear@1": 0.74, "ndcg_linear@5": 0.848256963051568, "ndcg_linear@10": 0.8595915384946303, "ndcg_exponential@1": 0.74, "ndcg_exponential@5": 0.848256963051568, "ndcg_exponential@10": 0.8595915384946303, "precision@1": 0.74, "precision@5": 0.18740000000000004, "precision@10": 0.0971, "recall@1": 0.74, "recall@5": 0.937, "recall@10": 0.971, "f1@1": 0.74, "f1@5": 0.31233333333333335, "f1@10": 0.1765454545454545, "map@1": 0.74, "map@5": 0.8183833333333334, "map@10": 0.8232611111111112, "mrr@1": 0.74, "mrr@5": 0.8183833333333334, "mrr@10": 0.8232611111111112, "num_pred": 1000, "num_data": 1000 }, "NIGHTS": { "hit@1": 0.687, "hit@5": 0.984, "hit@10": 0.996, "ndcg_linear@1": 0.687, "ndcg_linear@5": 0.8566435657801358, "ndcg_linear@10": 0.8605242972502368, "ndcg_exponential@1": 0.687, "ndcg_exponential@5": 0.8566435657801358, "ndcg_exponential@10": 0.8605242972502368, "precision@1": 0.687, "precision@5": 0.19680000000000003, "precision@10": 0.09960000000000001, "recall@1": 0.687, "recall@5": 0.984, "recall@10": 0.996, "f1@1": 0.687, "f1@5": 0.328, "f1@10": 0.18109090909090905, "map@1": 0.687, "map@5": 0.8132166666666667, "map@10": 0.8148154761904761, "mrr@1": 0.687, "mrr@5": 0.8132166666666667, "mrr@10": 0.8148154761904761, "num_pred": 1000, "num_data": 1000 }, "WebQA": { "hit@1": 0.907, "hit@5": 0.994, "hit@10": 0.996, "ndcg_linear@1": 0.907, "ndcg_linear@5": 0.9578107216104538, "ndcg_linear@10": 0.9585002621308952, "ndcg_exponential@1": 0.907, "ndcg_exponential@5": 0.9578107216104538, "ndcg_exponential@10": 0.9585002621308952, "precision@1": 0.907, "precision@5": 0.19880000000000003, "precision@10": 0.09960000000000002, "recall@1": 0.907, "recall@5": 0.994, "recall@10": 0.996, "f1@1": 0.907, "f1@5": 0.3313333333333333, "f1@10": 0.18109090909090905, "map@1": 0.907, "map@5": 0.9453833333333335, "map@10": 0.9456928571428572, "mrr@1": 0.907, "mrr@5": 0.9453833333333335, "mrr@10": 0.9456928571428572, "num_pred": 1000, "num_data": 1000 }, "FashionIQ": { "hit@1": 0.206, "hit@5": 0.459, "hit@10": 0.565, "ndcg_linear@1": 0.206, "ndcg_linear@5": 0.3388871924256756, "ndcg_linear@10": 0.37310755549414143, "ndcg_exponential@1": 0.206, "ndcg_exponential@5": 0.3388871924256756, "ndcg_exponential@10": 0.37310755549414143, "precision@1": 0.206, "precision@5": 0.0918, "precision@10": 0.0565, "recall@1": 0.206, "recall@5": 0.459, "recall@10": 0.565, "f1@1": 0.206, "f1@5": 0.15300000000000002, "f1@10": 0.10272727272727275, "map@1": 0.206, "map@5": 0.2990833333333333, "map@10": 0.31317222222222224, "mrr@1": 0.206, "mrr@5": 0.2990833333333333, "mrr@10": 0.31317222222222224, "num_pred": 1000, "num_data": 1000 }, "Wiki-SS-NQ": { "hit@1": 0.721, "hit@5": 0.905, "hit@10": 0.933, "ndcg_linear@1": 0.721, "ndcg_linear@5": 0.8245940831292553, "ndcg_linear@10": 0.8337255936944703, "ndcg_exponential@1": 0.721, "ndcg_exponential@5": 0.8245940831292553, "ndcg_exponential@10": 0.8337255936944703, "precision@1": 0.721, "precision@5": 0.18100000000000005, "precision@10": 0.09330000000000001, "recall@1": 0.721, "recall@5": 0.905, "recall@10": 0.933, "f1@1": 0.721, "f1@5": 0.3016666666666667, "f1@10": 0.1696363636363636, "map@1": 0.721, "map@5": 0.7972833333333333, "map@10": 0.8011015873015873, "mrr@1": 0.721, "mrr@5": 0.7972833333333333, "mrr@10": 0.8011015873015873, "num_pred": 1000, "num_data": 1000 }, "OVEN": { "hit@1": 0.74, "hit@5": 0.906, "hit@10": 0.943, "ndcg_linear@1": 0.74, "ndcg_linear@5": 0.8305855879211614, "ndcg_linear@10": 0.842757616838551, "ndcg_exponential@1": 0.74, "ndcg_exponential@5": 0.8305855879211614, "ndcg_exponential@10": 0.842757616838551, "precision@1": 0.74, "precision@5": 0.18120000000000006, "precision@10": 0.09430000000000001, "recall@1": 0.74, "recall@5": 0.906, "recall@10": 0.943, "f1@1": 0.74, "f1@5": 0.302, "f1@10": 0.17145454545454544, "map@1": 0.74, "map@5": 0.8052833333333334, "map@10": 0.8104293650793651, "mrr@1": 0.74, "mrr@5": 0.8052833333333334, "mrr@10": 0.8104293650793651, "num_pred": 1000, "num_data": 1000 }, "EDIS": { "hit@1": 0.926, "hit@5": 0.987, "hit@10": 0.994, "ndcg_linear@1": 0.926, "ndcg_linear@5": 0.9613923797345227, "ndcg_linear@10": 0.9637500661221646, "ndcg_exponential@1": 0.926, "ndcg_exponential@5": 0.9613923797345227, "ndcg_exponential@10": 0.9637500661221646, "precision@1": 0.926, "precision@5": 0.19740000000000005, "precision@10": 0.09940000000000002, "recall@1": 0.926, "recall@5": 0.987, "recall@10": 0.994, "f1@1": 0.926, "f1@5": 0.329, "f1@10": 0.18072727272727268, "map@1": 0.926, "map@5": 0.9526333333333334, "map@10": 0.9536619047619048, "mrr@1": 0.926, "mrr@5": 0.9526333333333334, "mrr@10": 0.9536619047619048, "num_pred": 1000, "num_data": 1000 }, "MSCOCO": { "hit@1": 0.741, "hit@5": 0.878, "hit@10": 0.916, "ndcg_linear@1": 0.741, "ndcg_linear@5": 0.8169582201963318, "ndcg_linear@10": 0.8291960694888117, "ndcg_exponential@1": 0.741, "ndcg_exponential@5": 0.8169582201963318, "ndcg_exponential@10": 0.8291960694888117, "precision@1": 0.741, "precision@5": 0.1756, "precision@10": 0.09160000000000001, "recall@1": 0.741, "recall@5": 0.878, "recall@10": 0.916, "f1@1": 0.741, "f1@5": 0.2926666666666667, "f1@10": 0.16654545454545452, "map@1": 0.741, "map@5": 0.7963666666666667, "map@10": 0.8013873015873015, "mrr@1": 0.741, "mrr@5": 0.7963666666666667, "mrr@10": 0.8013873015873015, "num_pred": 1000, "num_data": 1000 }, "RefCOCO": { "hit@1": 0.935, "hit@5": 0.997, "hit@10": 0.997, "ndcg_linear@1": 0.935, "ndcg_linear@5": 0.9727745888654012, "ndcg_linear@10": 0.9727745888654012, "ndcg_exponential@1": 0.935, "ndcg_exponential@5": 0.9727745888654012, "ndcg_exponential@10": 0.9727745888654012, "precision@1": 0.935, "precision@5": 0.19940000000000002, "precision@10": 0.09970000000000001, "recall@1": 0.935, "recall@5": 0.997, "recall@10": 0.997, "f1@1": 0.935, "f1@5": 0.33233333333333337, "f1@10": 0.18127272727272725, "map@1": 0.935, "map@5": 0.9643166666666667, "map@10": 0.9643166666666667, "mrr@1": 0.935, "mrr@5": 0.9643166666666667, "mrr@10": 0.9643166666666667, "num_pred": 1000, "num_data": 1000 }, "RefCOCO-Matching": { "hit@1": 0.941, "hit@5": 1.0, "hit@10": 1.0, "ndcg_linear@1": 0.941, "ndcg_linear@5": 0.9780939257071445, "ndcg_linear@10": 0.9780939257071445, "ndcg_exponential@1": 0.941, "ndcg_exponential@5": 0.9780939257071445, "ndcg_exponential@10": 0.9780939257071445, "precision@1": 0.941, "precision@5": 0.20000000000000004, "precision@10": 0.10000000000000002, "recall@1": 0.941, "recall@5": 1.0, "recall@10": 1.0, "f1@1": 0.941, "f1@5": 0.3333333333333333, "f1@10": 0.18181818181818182, "map@1": 0.941, "map@5": 0.9703333333333334, "map@10": 0.9703333333333334, "mrr@1": 0.941, "mrr@5": 0.9703333333333334, "mrr@10": 0.9703333333333334, "num_pred": 1000, "num_data": 1000 }, "Visual7W-Pointing": { "hit@1": 0.891, "hit@5": 0.956, "hit@10": 0.972, "ndcg_linear@1": 0.891, "ndcg_linear@5": 0.9271441470115078, "ndcg_linear@10": 0.9323059004032986, "ndcg_exponential@1": 0.891, "ndcg_exponential@5": 0.9271441470115078, "ndcg_exponential@10": 0.9323059004032986, "precision@1": 0.891, "precision@5": 0.19120000000000004, "precision@10": 0.09720000000000002, "recall@1": 0.891, "recall@5": 0.956, "recall@10": 0.972, "f1@1": 0.891, "f1@5": 0.31866666666666665, "f1@10": 0.17672727272727273, "map@1": 0.891, "map@5": 0.9174, "map@10": 0.9195269841269842, "mrr@1": 0.891, "mrr@5": 0.9174, "mrr@10": 0.9195269841269842, "num_pred": 1000, "num_data": 1000 } }, "video": { "K700": "DIR_N/A", "SmthSmthV2": "DIR_N/A", "HMDB51": "DIR_N/A", "UCF101": "DIR_N/A", "Breakfast": "DIR_N/A", "MVBench": "DIR_N/A", "Video-MME": "DIR_N/A", "NExTQA": "DIR_N/A", "EgoSchema": "DIR_N/A", "ActivityNetQA": "DIR_N/A", "DiDeMo": "DIR_N/A", "MSR-VTT": "DIR_N/A", "MSVD": "DIR_N/A", "VATEX": "DIR_N/A", "YouCook2": "DIR_N/A", "QVHighlight": "DIR_N/A", "Charades-STA": "DIR_N/A", "MomentSeeker": "DIR_N/A" }, "visdoc": { "ViDoRe_arxivqa": "DIR_N/A", "ViDoRe_docvqa": "DIR_N/A", "ViDoRe_infovqa": "DIR_N/A", "ViDoRe_tabfquad": "DIR_N/A", "ViDoRe_tatdqa": "DIR_N/A", "ViDoRe_shiftproject": "DIR_N/A", "ViDoRe_syntheticDocQA_artificial_intelligence": "DIR_N/A", "ViDoRe_syntheticDocQA_energy": "DIR_N/A", "ViDoRe_syntheticDocQA_government_reports": "DIR_N/A", "ViDoRe_syntheticDocQA_healthcare_industry": "DIR_N/A", "ViDoRe_esg_reports_human_labeled_v2": "DIR_N/A", "ViDoRe_biomedical_lectures_v2_multilingual": "DIR_N/A", "ViDoRe_economics_reports_v2_multilingual": "DIR_N/A", "ViDoRe_esg_reports_v2_multilingual": "DIR_N/A", "VisRAG_ArxivQA": "DIR_N/A", "VisRAG_ChartQA": "DIR_N/A", "VisRAG_MP-DocVQA": "DIR_N/A", "VisRAG_SlideVQA": "DIR_N/A", "VisRAG_InfoVQA": "DIR_N/A", "VisRAG_PlotQA": "DIR_N/A", "ViDoSeek-page": "DIR_N/A", "ViDoSeek-doc": "DIR_N/A", "MMLongBench-page": "DIR_N/A", "MMLongBench-doc": "DIR_N/A" } } }